© 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. 39179
    Prev
    Next
    INDEX
    Explanations

    district, or creek

    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
    liz
    -0.09
    etros
    -0.08
    ä¸įæĥ§
    -0.08
    æīĢåģļ
    -0.08
    theValue
    -0.08
    hots
    -0.08
    åįĬæŃ¥
    -0.08
    lahan
    -0.07
    /GPL
    -0.07
    _SPLIT
    -0.07
    POSITIVE LOGITS
    è½»
    0.07
    _slots
    0.07
     teg
    0.06
    aur
    0.06
    æ¹
    0.06
    _DEAD
    0.06
    è¿Ļåľ¨
    0.06
     سع
    0.06
    è¹Ī
    0.06
    ħ
    0.06
    Activations Density 1.320%

    No Known Activations