© 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. 33736
    Prev
    Next
    INDEX
    Explanations

    dip component or vector

    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
    eno
    -0.07
     decimal
    -0.07
    ç¼ĺåĪĨ
    -0.07
    å°ıæķ°
    -0.06
    ussy
    -0.06
    裾
    -0.06
    áĢ±áĢ¬
    -0.06
     Decimal
    -0.06
     rou
    -0.06
    USTA
    -0.06
    POSITIVE LOGITS
    çŁ¢éĩı
    0.10
     дип
    0.09
     vector
    0.09
    çŁ¢
    0.08
    vector
    0.08
    chooser
    0.08
    icap
    0.07
     reluctance
    0.07
    æĹ¥æĻļéĹ´
    0.07
    annotate
    0.07
    Activations Density 0.003%

    No Known Activations