© 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. 33033
    Prev
    Next
    INDEX
    Explanations

    synthesized, assembled, tempered, operative

    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
    æĹ¥æ¸IJ
    -0.07
    nest
    -0.07
    è¶Ĭä½İ
    -0.07
     dạo
    -0.07
    åĽ½åĨħå¸Ĥåľº
    -0.06
    ÙĦÙĬØ©
    -0.06
    æĪĸèĢħæĺ¯
    -0.06
    å¸Ĥåľºåıijå±ķ
    -0.06
    çijŀå®ī
    -0.06
    ason
    -0.06
    POSITIVE LOGITS
    å°Ĩè¿ĻäºĽ
    0.10
     nanti
    0.10
    å°Ĩåħ¶
    0.09
    å°ĨæīĢæľī
    0.08
    让è¿ĻäºĽ
    0.08
    å°Ĩå®ĥ们
    0.08
    å°Ĩ使
    0.08
    转åĮĸ为
    0.08
    åīįçļĦ
    0.08
     will
    0.08
    Activations Density 0.058%

    No Known Activations