© 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. 26195
    Prev
    Next
    INDEX
    Explanations

    numbers 1-9

    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
    izedName
    -0.07
    íĻľ
    -0.06
     Bearings
    -0.06
    cala
    -0.06
    åĽ°
    -0.06
    edar
    -0.06
    ä¸ĬåįĬå¹´
    -0.06
    ίδα
    -0.06
    ä¸ĬåįĬ
    -0.06
     bearing
    -0.06
    POSITIVE LOGITS
    anitize
    0.09
    ²
    0.08
    jom
    0.07
    æ¶Ľ
    0.07
    æĿ¡è¯Ħ论
    0.07
    åĬłåħ³æ³¨
    0.07
    æľĢæĸ°è¯Ħ论
    0.07
    Been
    0.07
    влека
    0.07
    erson
    0.07
    Activations Density 0.013%

    No Known Activations