© 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. 109433
    Prev
    Next
    INDEX
    Explanations

    gastr

    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
    ובי
    -0.08
    -U
    -0.07
    _g
    -0.07
     służ
    -0.07
    _Mod
    -0.07
    <string
    -0.07
     poking
    -0.07
     affirm
    -0.07
     Buck
    -0.07
    _TE
    -0.07
    POSITIVE LOGITS
    RouterModule
    0.08
     gastr
    0.08
    +":
    0.07
    気に
    0.07
     Classical
    0.07
    鳊
    0.07
     Later
    0.07
    Later
    0.07
    faces
    0.07
    喘
    0.07
    Activations Density 0.002%

    No Known Activations