© 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. 12740
    Prev
    Next
    INDEX
    Explanations

    update, edit, duplicate action

    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
    è¦ģéĹ»
    -0.08
    åĬłæĭī
    -0.07
    çīµ
    -0.07
    rando
    -0.07
    ikian
    -0.07
    éĤ£ä¸¤ä¸ª
    -0.07
    èĢĮéĻį
    -0.07
    åį´ä¸įæĺ¯
    -0.07
    æĪij们è¿ĺè¦ģ
    -0.07
    Unhandled
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪ
    0.07
    ستÙĩ
    0.06
    jat
    0.06
    _indent
    0.06
    plusplus
    0.06
     hall
    0.06
    át
    0.06
    é¦ĸåħĪè¦ģ
    0.06
    ieger
    0.06
    ç¾²
    0.06
    Activations Density 1.238%

    No Known Activations