© 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. 40438
    Prev
    Next
    INDEX
    Explanations

    nm followed by units like diameter, node, particles

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.11
    nya
    -0.09
    amen
    -0.09
    zlich
    -0.08
    æĿ¥å¾Ĺ
    -0.08
    /output
    -0.07
    adera
    -0.07
    onar
    -0.07
    åį«åĨķ
    -0.07
    odate
    -0.07
    POSITIVE LOGITS
    IMUM
    0.08
    дли
    0.07
     ago
    0.07
    以åĨħ
    0.07
    èĶ»
    0.07
    /native
    0.07
    ï¸İ
    0.07
    ç¥ī
    0.07
    é¢Ĩè¡Ķ
    0.07
    ICLES
    0.07
    Activations Density 0.010%

    No Known Activations