© 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. 75502
    Prev
    Next
    INDEX
    Explanations

    glob

    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
     presidents
    -0.07
    damn
    -0.07
     china
    -0.07
    诣
    -0.07
    大国
    -0.07
    accine
    -0.06
    واشنطن
    -0.06
     vợ
    -0.06
     Bordeaux
    -0.06
     moral
    -0.06
    POSITIVE LOGITS
    _routing
    0.07
    izr
    0.07
    asmine
    0.06
    谈起
    0.06
    disp
    0.06
     срок
    0.06
    .Mvc
    0.06
    (tm
    0.06
    idepress
    0.06
     discovers
    0.06
    Activations Density 0.045%

    No Known Activations