© 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. 22659
    Prev
    Next
    INDEX
    Explanations

    code

    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
    �от
    -0.07
    理由
    -0.07
     how
    -0.07
     malicious
    -0.06
    看他
    -0.06
     Medical
    -0.06
     Treat
    -0.06
    Truth
    -0.06
     caus
    -0.06
    slave
    -0.06
    POSITIVE LOGITS
     Rita
    0.07
    鲭
    0.07
     Sections
    0.06
     HLS
    0.06
     Residents
    0.06
    فير
    0.06
    粞
    0.06
    蹢
    0.06
     owner
    0.06
    [-
    0.06
    Activations Density 0.057%

    No Known Activations