© 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. 60858
    Prev
    Next
    INDEX
    Explanations

    squared change or difference

    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
    psilon
    -0.12
    <|box_end|>
    -0.11
    æĶ¾çŁ¢
    -0.10
    yms
    -0.09
    eam
    -0.09
    ystack
    -0.09
    ëģĶ
    -0.09
    thinkable
    -0.09
    eggio
    -0.09
    edReader
    -0.09
    POSITIVE LOGITS
    ../../../
    0.08
    ing
    0.08
    ic
    0.07
    lich
    0.07
    วà¸Ī
    0.06
    åľ¨
    0.06
    ãĥ³
    0.06
    i
    0.06
    en
    0.06
    atches
    0.06
    Activations Density 0.002%

    No Known Activations