© 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. 15-RESID-POST-AA
    11. 11103
    Prev
    Next
    INDEX
    Explanations

    free provided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Division
    -0.07
    (frame
    -0.06
    extensions
    -0.06
     totalTime
    -0.06
     Kre
    -0.06
    _Class
    -0.06
    �
    -0.06
    _source
    -0.06
    contrast
    -0.06
    ┃
    -0.06
    POSITIVE LOGITS
    愁
    0.08
     גופ
    0.07
    碛
    0.07
    隔壁
    0.07
     fe
    0.07
    忮
    0.07
     wager
    0.07
    わかって
    0.07
     oko
    0.07
    (~
    0.07
    Activations Density 0.879%

    No Known Activations