© 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. 11-RESID-POST-AA
    11. 75140
    Prev
    Next
    INDEX
    Explanations

    inverse

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tạm
    -0.07
     haunted
    -0.07
    umbai
    -0.07
    CEED
    -0.07
    תחר
    -0.06
    你自己
    -0.06
    Appending
    -0.06
    日正式
    -0.06
    ➩
    -0.06
    莫名其
    -0.06
    POSITIVE LOGITS
    ker
    0.07
    -Cola
    0.07
    ｆ
    0.07
    ｌ
    0.07
    /U
    0.07
    land
    0.07
     inequality
    0.07
    ке
    0.07
    urse
    0.07
     inverse
    0.07
    Activations Density 0.004%

    No Known Activations