© 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. 109683
    Prev
    Next
    INDEX
    Explanations

    .getElementById

    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
    艳
    -0.07
    헛
    -0.06
    붓
    -0.06
    双眼
    -0.06
     mamma
    -0.06
    复合
    -0.06
     lor
    -0.06
    قود
    -0.06
    aeper
    -0.06
     b
    -0.06
    POSITIVE LOGITS
    .books
    0.07
    ##_
    0.07
    を中心に
    0.07
    _SITE
    0.07
    ESPN
    0.07
    같
    0.07
    DeltaTime
    0.07
     deltas
    0.07
    	Entity
    0.07
    	State
    0.07
    Activations Density 0.000%

    No Known Activations