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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75664
    Prev
    Next
    INDEX
    Explanations

    terms

    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
    毛病
    -0.07
     onder
    -0.06
     itu
    -0.06
    vote
    -0.06
    chts
    -0.06
     powerless
    -0.06
    (ind
    -0.06
     ponder
    -0.06
    MPI
    -0.06
     jac
    -0.06
    POSITIVE LOGITS
    <Array
    0.08
     caliber
    0.07
    👅
    0.07
    .Hosting
    0.07
    .init
    0.07
    豉
    0.06
    Ң
    0.06
     Shemale
    0.06
    бой
    0.06
    שמש
    0.06
    Activations Density 0.001%

    No Known Activations