© 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. 41178
    Prev
    Next
    INDEX
    Explanations

    special characters, punctuation, symbols

    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
    cept
    -0.08
    à¶Ńà·Ĭ
    -0.07
    èĥ½è¢«
    -0.07
    ationally
    -0.07
    欲
    -0.06
    aram
    -0.06
    åĪº
    -0.06
    ilton
    -0.06
    èĥ½ä¸į
    -0.06
    è¸
    -0.06
    POSITIVE LOGITS
    æľ¬çīĪ
    0.08
    Äįa
    0.08
    _tC
    0.08
    åĽ¢ä½ĵ
    0.07
    /loader
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    ä¸Ĭéĺµ
    0.07
    ameni
    0.07
    æ°¸åħ´
    0.07
    é¾ĻåŁİ
    0.07
    Activations Density 0.044%

    No Known Activations