© 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. 8572
    Prev
    Next
    INDEX
    Explanations

    variable names in formulas

    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
    emm
    -0.08
    li
    -0.07
    -ves
    -0.07
    åīµ
    -0.07
    presso
    -0.07
    handler
    -0.07
    หลวà¸ĩ
    -0.06
     Thao
    -0.06
    èĤĩ
    -0.06
     presum
    -0.06
    POSITIVE LOGITS
    æľīè¿ij
    0.08
    åħ¶ä¸ŃæľĢ
    0.08
    aval
    0.07
    arina
    0.07
    ØŃاÙĦ
    0.07
    æ¯Ĥ
    0.07
     whose
    0.07
    rone
    0.07
     //~
    0.07
     بØŃÙĬØ«
    0.07
    Activations Density 0.010%

    No Known Activations