© 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. 41724
    Prev
    Next
    INDEX
    Explanations

    chemical formula

    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
    uum
    -0.08
    /lg
    -0.08
    pli
    -0.07
    _PD
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    serter
    -0.07
    æľĢåıĹ欢è¿İ
    -0.07
    çŃīä¸įèī¯
    -0.07
    fahrten
    -0.07
    erp
    -0.07
    POSITIVE LOGITS
    andang
    0.08
    æĶ¹æĢ§
    0.07
    ä¸īåı£
    0.07
    ä¸į详
    0.07
    /assets
    0.07
    gebung
    0.06
    chemical
    0.06
    æł¸å¯¹
    0.06
     ê·¸ëĮĢë¡ľ
    0.06
    èĥ½ä¸į
    0.06
    Activations Density 0.007%

    No Known Activations