© 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. 51494
    Prev
    Next
    INDEX
    Explanations

    read online

    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
    åĬłæĭ¿å¤§
    -0.08
    asta
    -0.08
    çĶļèĩ³æĺ¯
    -0.07
    çĶ¨èĩªå·±
    -0.07
    çĶļèĩ³åı¯ä»¥
    -0.07
    PropertyValue
    -0.07
    adari
    -0.07
    ä¹Łåı¯ä»¥åľ¨
    -0.07
    éĺ³åİ¿
    -0.07
    éĥ¨åĪĨåĨħ容
    -0.07
    POSITIVE LOGITS
    YPD
    0.06
    ục
    0.06
    lyn
    0.06
    个
    0.06
    ixon
    0.06
    å¸Īé£İ
    0.06
    ä¸įå¤ĸ
    0.06
    ATTR
    0.06
    èĤ¡ä»½
    0.06
    PRETTY
    0.06
    Activations Density 0.612%

    No Known Activations