© 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. 49570
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸Ī
    -0.07
    ogar
    -0.07
    GP
    -0.07
    CHA
    -0.07
    æľ¬ç½ij
    -0.06
    jam
    -0.06
     humanity
    -0.06
    <|box_end|>
    -0.06
    à¹Ģà¸Ľ
    -0.06
    æī«
    -0.06
    POSITIVE LOGITS
    ISTI
    0.07
    ATAB
    0.07
    icale
    0.07
    abee
    0.07
    itty
    0.06
    æIJº
    0.06
    uali
    0.06
    winkel
    0.06
    .vm
    0.06
    undler
    0.06
    Activations Density 0.000%

    No Known Activations