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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 29845
    Prev
    Next
    INDEX
    Explanations

    code

    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
    userinfo
    -0.07
    ource
    -0.07
     tấn
    -0.07
    _run
    -0.07
     landsc
    -0.07
     cruise
    -0.06
     Hait
    -0.06
    (interval
    -0.06
    スー�
    -0.06
    整合
    -0.06
    POSITIVE LOGITS
    (Entity
    0.07
    死了
    0.07
     clad
    0.07
     essentials
    0.06
     Semaphore
    0.06
     ü
    0.06
     Targets
    0.06
     unmarried
    0.06
     tbl
    0.06
    UNUSED
    0.06
    Activations Density 1.385%

    No Known Activations