© 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. 31504
    Prev
    Next
    INDEX
    Explanations

    floc separators, bubble separators

    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
    修身
    -0.08
    éļĶçĥŃ
    -0.08
    çĭĻåĩ»
    -0.07
    æľ¨éĽķ
    -0.07
     erased
    -0.07
    å±ħ家
    -0.07
    çĥ¤æ¼Ĩ
    -0.07
    éĢŀ
    -0.07
    走强
    -0.07
    æĭ
    -0.07
    POSITIVE LOGITS
    çī©æĸĻ
    0.09
     conveyor
    0.08
    RowCount
    0.08
    æ¯ıçıŃ
    0.08
    entr
    0.08
    éļ¾
    0.08
    åįłåľ°éĿ¢ç§¯
    0.07
    heu
    0.07
    gravity
    0.07
     fou
    0.07
    Activations Density 0.071%

    No Known Activations