© 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. 20108
    Prev
    Next
    INDEX
    Explanations

    interval, class, intermediary, way

    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
    adari
    -0.07
    egas
    -0.07
    ä¸Ģå¤ľ
    -0.06
    é»į
    -0.06
    |
    -0.06
    稻
    -0.06
    éĥ½æĺ¯ä»İ
    -0.06
    Wake
    -0.06
     always
    -0.06
     worry
    -0.06
    POSITIVE LOGITS
    _BLEND
    0.08
    ¹Ħ
    0.08
    âĢ¦]
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.08
     Gewerk
    0.08
    [opt
    0.08
    zne
    0.07
    åĪģ
    0.07
    tvr
    0.07
    .bundle
    0.07
    Activations Density 0.001%

    No Known Activations