© 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. 17261
    Prev
    Next
    INDEX
    Explanations

    is a placeholder

    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
    ä¸Ģè¯į
    -0.10
    ä¸ĢåĪĩ
    -0.10
    sWith
    -0.10
    ä¸ĢäºĽ
    -0.09
    ä¸Ģè¨Ģ
    -0.09
    ä¸Ģå¹´çļĦ
    -0.09
    ä¸Ģ天çļĦ
    -0.09
     ìĿ´ëĬĶ
    -0.08
    ä¸Ģ
    -0.08
    ×Ķ
    -0.08
    POSITIVE LOGITS
    à¹Ħà¸Ľà¸ķาม
    0.12
    éĤ£ä¹ĪçļĦ
    0.12
    /is
    0.11
    åIJįåī¯åħ¶å®ŀçļĦ
    0.11
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.11
    otope
    0.10
    ä¸įéĶĻçļĦéĢīæĭ©
    0.10
    ãģĺãĤģãģ¦
    0.10
    ãģ£ãģįãĤĬ
    0.10
    æĻĤåĢĻ
    0.10
    Activations Density 0.003%

    No Known Activations