© 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. 43532
    Prev
    Next
    INDEX
    Explanations

    chromosome arms p and q

    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
    çĦ
    -0.08
    æ·Ĩ
    -0.08
    é¤
    -0.08
    agas
    -0.07
    ieber
    -0.07
    otka
    -0.07
    å¹´åģĩ
    -0.07
    ayah
    -0.07
    adrid
    -0.07
    çĸĻ
    -0.07
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.08
    åħ¨éķ¿
    0.07
    adol
    0.07
    ä¸Ĭä¸į
    0.07
    ä¸Ĭ没æľī
    0.07
    åĽ¾è°±
    0.07
    ä¸ŃåĮ»èį¯
    0.07
    ä¸Ĭè¿ĺ
    0.06
    çĶµåŃIJä¿¡æģ¯
    0.06
    esome
    0.06
    Activations Density 0.077%

    No Known Activations