© 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. 56748
    Prev
    Next
    INDEX
    Explanations

    radio buttons

    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
    LIO
    -0.09
    TRIB
    -0.09
    doa
    -0.09
    лÑĮÑĦ
    -0.09
    zos
    -0.09
    ulls
    -0.08
    æѦç¥ŀ
    -0.08
    ppv
    -0.08
    REEN
    -0.08
    hada
    -0.08
    POSITIVE LOGITS
    ini
    0.08
    ty
    0.07
    ur
    0.07
    ot
    0.07
    ä¸ĭåIJĮ
    0.06
    ore
    0.06
    2
    0.06
    er
    0.06
     anymore
    0.06
    æ¸ħæµģ
    0.06
    Activations Density 0.005%

    No Known Activations