© 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. 75296
    Prev
    Next
    INDEX
    Explanations

    (function

    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
     manipulate
    -0.07
    IS
    -0.07
    😲
    -0.07
    轨
    -0.07
    beat
    -0.07
    ThreadPool
    -0.07
    可想
    -0.07
     президент
    -0.07
    昀
    -0.06
     своими
    -0.06
    POSITIVE LOGITS
    ᘗ
    0.08
     Marks
    0.07
    ера
    0.07
    爭
    0.07
    losing
    0.06
    _WIDGET
    0.06
    耗费
    0.06
    _problem
    0.06
    ㈬
    0.06
     Closure
    0.06
    Activations Density 0.014%

    No Known Activations