© 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. 1818
    Prev
    Next
    INDEX
    Explanations

    public good / shared interest

    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
    ulta
    -0.07
    å¤ĸäºĭ
    -0.07
     dow
    -0.07
    entin
    -0.07
    æľīä¸Ģçķª
    -0.07
    åIJĥèĤī
    -0.07
    饰
    -0.06
    åħ¨éĿ¢è´¯å½»
    -0.06
    åѦç±į
    -0.06
     kontakt
    -0.06
    POSITIVE LOGITS
    åħ¬åħ±
    0.13
    åħ±äº«
    0.12
    (public
    0.12
    åħ¬åħ±è®¾æĸ½
    0.12
    åħ¬åħ±èµĦæºIJ
    0.12
    /shared
    0.11
    (shared
    0.11
    shared
    0.11
    åħ¬åħ±åĪ©çĽĬ
    0.11
     shared
    0.11
    Activations Density 0.016%

    No Known Activations