© 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. 29633
    Prev
    Next
    INDEX
    Explanations

    third categorical

    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
    antino
    -0.07
    er
    -0.07
    ungan
    -0.07
    iners
    -0.06
     itself
    -0.06
    åĻ¨çŃī
    -0.06
    ÙĬب
    -0.06
    els
    -0.06
     himself
    -0.06
    ungen
    -0.06
    POSITIVE LOGITS
    ²
    0.08
    zinha
    0.08
    °
    0.08
    :NO
    0.08
    kez
    0.07
    zc
    0.07
    nière
    0.07
    aca
    0.07
     ника
    0.07
    £
    0.07
    Activations Density 0.001%

    No Known Activations