© 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. 45640
    Prev
    Next
    INDEX
    Explanations

    json-like structures with non-latin characters

    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
    ä¸ĭåIJĮ
    -0.06
    æĻ°
    -0.06
    å¤§åľ£
    -0.06
    è¿ŁæĹ©
    -0.06
    pc
    -0.06
    éĺģä¸ĭ
    -0.06
    è©°
    -0.06
    hei
    -0.06
     emb
    -0.06
    ev
    -0.06
    POSITIVE LOGITS
    ارب
    0.09
    ä¸Ģåıį
    0.08
    าà¸ģลาà¸ĩ
    0.07
    ä¸Ģæĭį
    0.07
    è¶Ĭæĥ³
    0.07
    --[[
    0.07
    aviolet
    0.07
    itecture
    0.07
    LastError
    0.07
    AndHashCode
    0.07
    Activations Density 0.137%

    No Known Activations