© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63039
    Prev
    Next
    INDEX
    Explanations

    code ending in parenthesis/semicolon

    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
    为æĤ¨ä»ĭç»į
    -0.07
    Lint
    -0.07
    .isNullOrEmpty
    -0.07
    vene
    -0.07
    "]=>
    -0.06
    åѦåı²
    -0.06
     })(
    -0.06
    _UNUSED
    -0.06
    __:
    -0.06
    æĹłéĹ»
    -0.06
    POSITIVE LOGITS
    éĽ
    0.08
    ommage
    0.07
    ãĤ¥
    0.07
    å´Ķ
    0.07
    å¢ĥçķĮ
    0.07
    avenport
    0.07
    ç©
    0.07
    atoria
    0.07
     tonel
    0.07
    å»
    0.07
    Activations Density 0.116%

    No Known Activations