© 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. 41958
    Prev
    Next
    INDEX
    Explanations

    Require Licensed

    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
    fan
    -0.08
    akes
    -0.07
    žd
    -0.07
    mp
    -0.07
    abouts
    -0.07
     <![
    -0.06
    sem
    -0.06
    设å¤ĩè¿Ľè¡Į
    -0.06
    fonds
    -0.06
    _unique
    -0.06
    POSITIVE LOGITS
    ppo
    0.08
    iato
    0.08
    istri
    0.07
    ï¸İ
    0.07
    icto
    0.07
    plar
    0.07
    ezi
    0.06
    atsu
    0.06
    ié
    0.06
    éĽ
    0.06
    Activations Density 0.084%

    No Known Activations