© 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. 13122
    Prev
    Next
    INDEX
    Explanations

    natural habitat

    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
    åĵī
    -0.09
    èĢĮ代ä¹ĭ
    -0.09
    Ñħла
    -0.08
    fabric
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    겸
    -0.08
    WORDS
    -0.08
    CORD
    -0.08
    Pragma
    -0.08
    ",&
    -0.07
    POSITIVE LOGITS
    ...
    0.06
    ç»Ĩ
    0.06
    sd
    0.06
    utt
    0.06
    èĦ¯
    0.06
    uche
    0.06
    ber
    0.06
    麦èĬ½
    0.05
    iot
    0.05
     entr
    0.05
    Activations Density 0.516%

    No Known Activations