© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9141
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    ness
    -0.11
    åĬłæĭ¿å¤§
    -0.10
    s
    -0.10
    ات
    -0.09
    adera
    -0.09
    ség
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    è¡«
    -0.08
    åħĭéļ¾
    -0.07
    POSITIVE LOGITS
    ailleurs
    0.09
    ivative
    0.09
    ãĤĪãģĨãģª
    0.08
    ãģ£ãģĵ
    0.08
    precated
    0.08
    yled
    0.08
    ungeons
    0.08
    ihkan
    0.07
    ами
    0.07
    ate
    0.07
    Activations Density 0.009%

    No Known Activations