© 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. 56320
    Prev
    Next
    INDEX
    Explanations

    code, loop, interface

    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
    rega
    -0.08
    端
    -0.07
    beck
    -0.07
    ²
    -0.07
    åį¯
    -0.06
    ukah
    -0.06
    å¥ī
    -0.06
    æľĪä¸ĬæŬ
    -0.06
    æIJ¬
    -0.06
    éľ²
    -0.06
    POSITIVE LOGITS
    <|fim_suffix|>
    0.08
    áž
    0.08
    ä¸įåı¯æĢĿè®®
    0.07
     ())
    0.07
     redund
    0.07
    دÙĬØ©
    0.07
    alp
    0.07
    leks
    0.06
    ulary
    0.06
    .Binary
    0.06
    Activations Density 0.009%

    No Known Activations