© 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. 49460
    Prev
    Next
    INDEX
    Explanations

    compose or choose

    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
    zelf
    -0.11
    <|box_end|>
    -0.10
    uzzi
    -0.10
    imiter
    -0.10
    spur
    -0.09
    nowled
    -0.09
    ÅŁe
    -0.09
    tores
    -0.09
    enburg
    -0.09
    æĢ»ç½²
    -0.09
    POSITIVE LOGITS
    ptions
    0.08
    i
    0.07
    ×Ļ
    0.07
    ption
    0.07
    ÅĻejmÄĽ
    0.07
    ephy
    0.06
     halinde
    0.06
    åIJĪçī©
    0.06
    ombies
    0.06
    illet
    0.06
    Activations Density 0.001%

    No Known Activations