© 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. 42032
    Prev
    Next
    INDEX
    Explanations

    programming code structures

    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
    cente
    -0.09
    *',
    -0.09
    åį³éĢĿ
    -0.08
    anca
    -0.08
    arani
    -0.08
    arate
    -0.08
    <"
    -0.07
    .ci
    -0.07
     ("<
    -0.07
     bá
    -0.07
    POSITIVE LOGITS
     \"
    0.07
     ____
    0.07
     ______
    0.07
    \"
    0.06
     Enth
    0.06
    erox
    0.06
    ____
    0.06
    \n
    0.06
    E
    0.05
    n
    0.05
    Activations Density 0.028%

    No Known Activations