© 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. 3093
    Prev
    Next
    INDEX
    Explanations

    /bin/env interpreters

    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
    ª½
    -0.32
    ´ī
    -0.27
    xeda
    -0.26
    ¿Į
    -0.26
    ®¤
    -0.26
    {EIF
    -0.26
    "urls
    -0.26
    ŃĶ
    -0.26
    tijk
    -0.25
    >manual
    -0.25
    POSITIVE LOGITS
    <|endoftext|>
    0.08
    0.07
    .
    0.07
    -
    0.07
    S
    0.07
    ...
    0.07
    ;
    0.06
    /
    0.06
    '
    0.06
    ,
    0.06
    Activations Density 18.686%

    No Known Activations