© 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. 7311
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    itemid
    -0.09
    åݦ
    -0.08
    æ³Ĺ
    -0.08
    _baseline
    -0.08
    ambo
    -0.08
    ä»¥ä¹łè¿ijå¹³åIJĮå¿Ĺä¸ºæł¸å¿ĥçļĦåħļä¸Ń央
    -0.08
    ISI
    -0.08
    _BOTH
    -0.07
    大åIJī
    -0.07
    /rfc
    -0.07
    POSITIVE LOGITS
    irate
    0.08
    uir
    0.07
    unky
    0.07
     unknown
    0.07
     eh
    0.06
    ë¶ĦìĹIJ
    0.06
    èĭ¥æľī
    0.06
    unknown
    0.06
    å¾Īå¤ļåľ°æĸ¹
    0.06
    med
    0.06
    Activations Density 0.077%

    No Known Activations