© 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. 44937
    Prev
    Next
    INDEX
    Explanations

    licensed under the MIT and GPL licenses

    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
    好çľĭçļĦ
    -0.07
    æĥ¯
    -0.07
    çķľ
    -0.07
    alaman
    -0.07
    LEAN
    -0.07
    avo
    -0.07
    ç©
    -0.07
    è£
    -0.07
    zyd
    -0.07
    EEDED
    -0.07
    POSITIVE LOGITS
    æľĢåIJİåľ¨
    0.07
    icha
    0.07
    inkan
    0.07
    ç»ĵæŀľè¡¨æĺİ
    0.06
    tery
    0.06
    以西
    0.06
    æľĢç»Ī以
    0.06
    west
    0.06
    令æĪij
    0.06
    elor
    0.06
    Activations Density 0.007%

    No Known Activations