© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 28511
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    multiple-choice question-and-answer structure and selection cues (option letters, enumerated choices, and related numeric details like dates or counts).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undis
    -0.07
    legend
    -0.07
     thả
    -0.07
    公认
    -0.07
    Set
    -0.06
     Trash
    -0.06
    Extension
    -0.06
    estado
    -0.06
     evidence
    -0.06
     departamento
    -0.06
    POSITIVE LOGITS
    럴
    0.07
    +[
    0.07
    博彩
    0.07
     Fill
    0.07
    肢
    0.06
    ങ
    0.06
    (IT
    0.06
    免除
    0.06
    模仿
    0.06
    .RequestMethod
    0.06
    Activations Density 0.341%

    No Known Activations