© 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. 28638
    Prev
    Next
    INDEX
    Explanations

    requested information or action

    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
    .perform
    -0.08
    -columns
    -0.08
    kost
    -0.08
    acson
    -0.07
    nova
    -0.07
    hind
    -0.07
    oulouse
    -0.07
    <|fim_prefix|>
    -0.07
    byt
    -0.07
     Gors
    -0.07
    POSITIVE LOGITS
    ä¿ĥ
    0.06
    rokes
    0.06
    beck
    0.06
    Ø«ÙĦØ©
    0.06
    å¹´ä»ħ
    0.06
    onger
    0.06
    0.06
    ark
    0.06
    inta
    0.06
    ong
    0.06
    Activations Density 0.007%

    No Known Activations