© 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. 109684
    Prev
    Next
    INDEX
    Explanations

    light/sunlight

    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
     thousands
    -0.08
    储备
    -0.07
     Cruiser
    -0.07
    价位
    -0.07
     Exceptions
    -0.07
    uche
    -0.07
    一审
    -0.07
     Predicate
    -0.07
     lumière
    -0.07
    ios
    -0.07
    POSITIVE LOGITS
     merchants
    0.07
     YES
    0.07
    Encryption
    0.07
     öğren
    0.07
    に入った
    0.07
    .setContentType
    0.07
    擠
    0.07
     wid
    0.07
    略有
    0.07
     startPosition
    0.07
    Activations Density 0.003%

    No Known Activations