© 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. 42785
    Prev
    Next
    INDEX
    Explanations

    neural networks and resin

    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
    din
    -0.07
    å¼łæĻĵ
    -0.07
    è··
    -0.07
    IRES
    -0.07
    ëłģ
    -0.07
    LAND
    -0.07
    оÑı
    -0.07
    ×Ĺ×Ļ
    -0.07
    æį·
    -0.07
    MZ
    -0.07
    POSITIVE LOGITS
    çĽ²
    0.07
    aber
    0.07
    ront
    0.07
    å²±
    0.07
    ittel
    0.06
     Invocation
    0.06
    ulfilled
    0.06
     Metric
    0.06
    erver
    0.06
     gal
    0.06
    Activations Density 0.610%

    No Known Activations