© 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. 55369
    Prev
    Next
    INDEX
    Explanations

    potential, activity, and states

    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
    {"
    -0.07
    åıĸå¾ĹçļĦæĪIJ绩
    -0.06
    (("
    -0.06
    ~
    -0.06
    ossa
    -0.06
    æ£ĢæŁ¥ä¸Ģä¸ĭ
    -0.06
    uels
    -0.06
    abilia
    -0.06
    åħ³å¿ĥçļĦéĹ®é¢ĺ
    -0.05
     ded
    -0.05
    POSITIVE LOGITS
     (`
    0.12
     (**
    0.11
     (*
    0.10
     (__
    0.10
     (\
    0.10
     abbreviated
    0.10
     (:
    0.10
     ($
    0.09
     (/
    0.09
    abbrev
    0.09
    Activations Density 0.284%

    No Known Activations