© 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. 51088
    Prev
    Next
    INDEX
    Explanations

    code prefixes

    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
    å¹³åı°åĴĮ
    -0.06
    oret
    -0.06
    èĩªè§īæĢ§
    -0.06
    plot
    -0.06
     paras
    -0.05
    à¹ģà¸ģà¹Ī
    -0.05
    ä»·æł¼æĺ¯
    -0.05
    uches
    -0.05
    añ
    -0.05
    ä¸įå®ľ
    -0.05
    POSITIVE LOGITS
    <|box_end|>
    0.08
    ×Ŀ
    0.08
    sworth
    0.08
    itto
    0.08
    ichte
    0.08
    <tool_response>
    0.07
    Ĺ
    0.07
    åħ®
    0.07
    ernote
    0.07
    ftware
    0.07
    Activations Density 0.039%

    No Known Activations