© 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. 49151
    Prev
    Next
    INDEX
    Explanations

    decisions and statements

    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
    åĪĿä¸ŃçĶŁ
    -0.08
     Strict
    -0.07
    lor
    -0.07
     reputed
    -0.07
     ÑıкобÑĭ
    -0.07
    .Strict
    -0.07
    eful
    -0.07
    Strict
    -0.07
     rivals
    -0.07
    arik
    -0.07
    POSITIVE LOGITS
     gotta
    0.08
     freaking
    0.08
     $#
    0.08
    Thunk
    0.07
     fucking
    0.07
    æĹłè®ºä½ł
    0.07
    çłĶ究表æĺİ
    0.07
    éľĢè¦ģæĪij们
    0.07
    æĪij们就è¦ģ
    0.07
     itulah
    0.07
    Activations Density 2.114%

    No Known Activations