© 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. 32300
    Prev
    Next
    INDEX
    Explanations

    larvae feed on or adults are

    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
    oco
    -0.08
    ä½łä¸įçŁ¥éģĵ
    -0.08
    ischt
    -0.07
    ymes
    -0.07
    å°±åĥıä¸Ģ个
    -0.07
    èĭ¥ä¸įæĺ¯
    -0.07
    æĪijä»¬çĽ¸ä¿¡
    -0.07
    atti
    -0.07
    åĥıä¸Ģ个
    -0.07
    <|box_end|>
    -0.07
    POSITIVE LOGITS
     firstly
    0.07
    å·¥ç¨ĭ建设
    0.07
    quest
    0.07
    åĭī
    0.06
     cac
    0.06
    eneric
    0.06
    çŁ¥åħ¶
    0.06
     unsuccessfully
    0.06
    ä»ħä¾Ľ
    0.06
    åIJĮæĹ¥
    0.06
    Activations Density 1.831%

    No Known Activations