© 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. 12695
    Prev
    Next
    INDEX
    Explanations

    code delimiters or structure

    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
    åıĪå¦Ĥ
    -0.08
    çļĦèī¯å¥½
    -0.07
    ets
    -0.07
    <|box_end|>
    -0.07
     <",
    -0.07
    ä¸įè°ĥ
    -0.06
    noinspection
    -0.06
     "}
    -0.06
     garde
    -0.06
    åıĪåĥı
    -0.06
    POSITIVE LOGITS
    aveur
    0.08
    olist
    0.07
    .;
    0.06
    åºĨ
    0.06
    IMIZE
    0.06
    Ascii
    0.06
    _aliases
    0.06
    spielen
    0.06
    verband
    0.06
    ä¸į详
    0.06
    Activations Density 0.105%

    No Known Activations