© 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. 15456
    Prev
    Next
    INDEX
    Explanations

    data structures and formatting

    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
    妾
    -0.07
    ieg
    -0.07
     Terb
    -0.07
    åľ¨èIJ¥
    -0.07
    راج
    -0.07
    éĹª
    -0.07
    å½ĵ社
    -0.06
    Öĩ
    -0.06
    uppen
    -0.06
    è´§
    -0.06
    POSITIVE LOGITS
    忱
    0.08
    ulich
    0.07
     tact
    0.07
    asten
    0.07
    ubb
    0.07
    lá
    0.07
    vect
    0.07
    ắp
    0.06
    lios
    0.06
    lut
    0.06
    Activations Density 0.008%

    No Known Activations