© 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. 21009
    Prev
    Next
    INDEX
    Explanations

    Âł entries

    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
    pes
    -0.08
    esp
    -0.07
    quirrel
    -0.07
    les
    -0.07
    à³į
    -0.07
    zelt
    -0.07
    oller
    -0.07
    anes
    -0.07
    psilon
    -0.07
    holz
    -0.07
    POSITIVE LOGITS
    éĿĴéĿĴ
    0.09
    óp
    0.08
    åĭĩå¾Ģ缴åīį
    0.07
    æIJŃ
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    InstanceOf
    0.06
    Ñĩан
    0.06
    çŃĶæ¡Ī解æŀIJ
    0.06
     Thornton
    0.06
    angeb
    0.06
    Activations Density 0.024%

    No Known Activations