© 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. 19-RESID-POST-AA
    11. 8081
    Prev
    Next
    INDEX
    Explanations

    Questions and conversations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     منه
    -0.08
    툰
    -0.07
    Ḿ
    -0.07
    reek
    -0.07
    杀菌
    -0.07
    되지
    -0.07
    食べた
    -0.06
    汉字
    -0.06
    ◣
    -0.06
    繪
    -0.06
    POSITIVE LOGITS
     activity
    0.07
     importance
    0.07
    [g
    0.07
     państ
    0.07
    laws
    0.07
     assistance
    0.06
    的表情
    0.06
     sponsors
    0.06
    ,A
    0.06
     foundations
    0.06
    Activations Density 0.103%

    No Known Activations