© 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. 31531
    Prev
    Next
    INDEX
    Explanations

    copyright and file declarations

    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
    âĢ¦).
    -0.08
    imaan
    -0.07
    Ø©
    -0.07
    istr
    -0.07
    $MESS
    -0.07
    erede
    -0.07
    ergestellt
    -0.07
    âĢ¦),
    -0.07
    agre
    -0.07
    Porno
    -0.07
    POSITIVE LOGITS
    èĩªå·±
    0.09
    ings
    0.07
    en
    0.07
    å°Ĩ
    0.07
    пол
    0.06
    nbsp
    0.06
    0.06
    ľ
    0.06
    ا
    0.06
    å«ī
    0.06
    Activations Density 0.101%

    No Known Activations