© 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. 29349
    Prev
    Next
    INDEX
    Explanations

    influence of

    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
    ê¹IJ
    -0.12
    este
    -0.10
    ãĥĥãĤ¯
    -0.09
    Ø©
    -0.09
    خداÙħ
    -0.08
    ification
    -0.08
    عاÙĨ
    -0.08
    à¯įà®ķ
    -0.08
    apiro
    -0.08
    kenal
    -0.08
    POSITIVE LOGITS
    æ·±è¿ľ
    0.08
    nahme
    0.08
    lessly
    0.08
    پذ
    0.07
    ments
    0.07
    lesh
    0.07
    ηÏĤ
    0.07
    ably
    0.07
    äºĨèĩªå·±
    0.07
    a
    0.07
    Activations Density 0.051%

    No Known Activations