© 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. 1586
    Prev
    Next
    INDEX
    Explanations

    operations

    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
     Highway
    -0.07
    inging
    -0.07
    .production
    -0.07
     bezpoś
    -0.07
    _primitive
    -0.07
     budd
    -0.07
    总额
    -0.07
     strokeLine
    -0.06
    hoot
    -0.06
    _widget
    -0.06
    POSITIVE LOGITS
    Bu
    0.07
    こともあります
    0.07
     Pakistan
    0.07
    绪
    0.07
    🚑
    0.07
    azaar
    0.06
    כתוב
    0.06
     ABI
    0.06
     UITableViewDataSource
    0.06
    员工
    0.06
    Activations Density 0.006%

    No Known Activations