© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39308
    Prev
    Next
    INDEX
    Explanations

    feature extraction and selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _PRIORITY
    -0.09
     dây
    -0.08
    betrieb
    -0.07
    èµĦæºIJéħįç½®
    -0.07
    ç¼ĸ审
    -0.07
    antil
    -0.07
     berlaku
    -0.07
     fragr
    -0.06
    afil
    -0.06
    COPE
    -0.06
    POSITIVE LOGITS
     preprocessing
    0.10
     raw
    0.09
    è¿ĻäºĽæķ°æį®
    0.09
    çIJĨåĮĸ
    0.08
    raw
    0.08
     preprocess
    0.08
    å¤ļç»´
    0.08
     extracted
    0.08
    å¤ļ维度
    0.08
    éĢģåħ¥
    0.07
    Activations Density 0.082%

    No Known Activations