© 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. 45834
    Prev
    Next
    INDEX
    Explanations

    _for

    np_max-act · gemini-2.0-flash
    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
    参数
    -0.07
     Wh
    -0.07
     pers
    -0.07
     mush
    -0.07
    minor
    -0.06
    hari
    -0.06
     Mutable
    -0.06
     keto
    -0.06
     arrangement
    -0.06
     terms
    -0.06
    POSITIVE LOGITS
    ocities
    0.08
     counties
    0.08
    _icall
    0.07
     SelectList
    0.07
    .Est
    0.07
    Ϋ
    0.07
    学堂
    0.07
    戡
    0.06
    .inventory
    0.06
    .front
    0.06
    Activations Density 0.001%

    No Known Activations