© 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. 18409
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    å¿ĹåĪļ
    -0.07
    |#
    -0.07
    olog
    -0.07
    |%
    -0.07
    ave
    -0.06
    <|im_start|>
    -0.06
    poses
    -0.06
    utch
    -0.06
     |_
    -0.06
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.06
    POSITIVE LOGITS
    arz
    0.08
    jos
    0.08
    åīįèĢħ
    0.07
    IfExists
    0.07
    æ³£
    0.07
    çľ¼èĬ±ç¼Ń
    0.07
     enfin
    0.07
    _launcher
    0.07
    çŃīçŃī
    0.07
    åħ°è¾¾
    0.07
    Activations Density 0.051%

    No Known Activations