© 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. 39253
    Prev
    Next
    INDEX
    Explanations

    LaTeX document 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
    ness
    -0.07
    a
    -0.07
    iswa
    -0.06
    ambah
    -0.06
    ington
    -0.06
    mehr
    -0.06
    ا
    -0.06
    /
    -0.06
    odob
    -0.06
    aly
    -0.06
    POSITIVE LOGITS
    irão
    0.10
    <|box_end|>
    0.09
    jal
    0.09
    ónimo
    0.08
     latter
    0.08
    odore
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    åħĭåĬĽ
    0.08
    _tex
    0.08
    ä½Ĩæĺ¯ä½ł
    0.08
    Activations Density 0.011%

    No Known Activations