© 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. 45040
    Prev
    Next
    INDEX
    Explanations

    otherwise/contrary

    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
    盥
    -0.08
    𝚋
    -0.07
     descent
    -0.07
    惊
    -0.07
    -xs
    -0.07
    それ
    -0.07
     borderWidth
    -0.07
     הדברים
    -0.07
    <Transaction
    -0.07
     Freund
    -0.07
    POSITIVE LOGITS
    protocols
    0.07
    RGBO
    0.07
    "',
    0.07
    REFERENCE
    0.07
    〈
    0.07
     Penguin
    0.07
    Research
    0.07
     yapıl
    0.07
    Saving
    0.06
    DateTime
    0.06
    Activations Density 0.006%

    No Known Activations