© 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. 45529
    Prev
    Next
    INDEX
    Explanations

    negative numbers

    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
    ford
    -0.07
    kd
    -0.07
    kb
    -0.06
    ил
    -0.06
    chow
    -0.06
    en
    -0.06
    nop
    -0.06
    st
    -0.06
    y
    -0.06
    chetti
    -0.06
    POSITIVE LOGITS
    ä¸ĢæľŁ
    0.09
    çŃĶ主
    0.09
    onds
    0.08
    ixo
    0.07
    å¸ĮæľĽå¯¹æĤ¨
    0.07
    _CAST
    0.07
    {'
    0.07
    eros
    0.07
    attle
    0.07
    áĥĵáĥĶ
    0.07
    Activations Density 0.024%

    No Known Activations