© 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. 23458
    Prev
    Next
    INDEX
    Explanations

    UNITED STATES

    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
    èĩªå·±
    -0.14
    èĩªå·±æ²¡æľī
    -0.12
    èĩªå·±è¢«
    -0.11
    èĩªå·±èº«ä¸Ĭ
    -0.09
    tempts
    -0.09
    -0.09
    каÑĥ
    -0.08
    puis
    -0.08
    gether
    -0.08
    parency
    -0.07
    POSITIVE LOGITS
    ãĤıãģijãģ§
    0.07
    ãģĹãģıãģ¯
    0.07
    gle
    0.07
    ়
    0.07
    iomanip
    0.06
    D
    0.06
    ropol
    0.06
    0.06
    以ä¸ĭæĺ¯
    0.06
    ady
    0.06
    Activations Density 0.028%

    No Known Activations