© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42584
    Prev
    Next
    INDEX
    Explanations

    Also, furthermore, questions

    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
    ola
    -0.07
    te
    -0.06
    ç§ijæĬĢåıijå±ķæľīéĻIJåħ¬åı¸
    -0.06
    æ¯Ķä¸įä¸Ĭ
    -0.06
    ste
    -0.06
    FC
    -0.06
    Ļ
    -0.06
    dem
    -0.06
    大路
    -0.06
    ози
    -0.06
    POSITIVE LOGITS
    åı¦ä¸ĢåĢĭ
    0.09
    ":-
    0.08
    -shadow
    0.08
    구ìļĶ
    0.07
    кои
    0.07
    burgh
    0.07
    ugo
    0.07
     Sprecher
    0.07
    åĬŁ
    0.07
    _drop
    0.07
    Activations Density 0.206%

    No Known Activations