© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20336
    Prev
    Next
    INDEX
    Explanations

    word endings followed by parentheses

    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
     (
    -0.09
    (
    -0.08
    />.
    -0.08
    '},
    -0.07
    *',
    -0.07
    ï¼Ī
    -0.07
    ;if
    -0.07
    %;">
    -0.07
    ."),
    -0.07
     flat
    -0.07
    POSITIVE LOGITS
    <|box_end|>
    0.08
    جÙĬ
    0.08
    _unregister
    0.08
    ancock
    0.08
    ï¼ī
    0.08
    agens
    0.07
    çĻ»è®°çļĦ
    0.07
    OTH
    0.07
    elter
    0.07
    JsonValue
    0.07
    Activations Density 0.155%

    No Known Activations