© 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. 22233
    Prev
    Next
    INDEX
    Explanations

    local function theorems

    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
    âu
    -0.09
    æı½
    -0.08
    .collection
    -0.07
    adoria
    -0.07
    åĬłéĩį
    -0.07
    æķ¬èĢģ
    -0.07
    UMMY
    -0.07
    JsonObject
    -0.07
     Fool
    -0.07
    tones
    -0.07
    POSITIVE LOGITS
     locally
    0.10
    å±Ģéĥ¨
    0.09
     Loc
    0.09
     nearby
    0.08
    åħīæ»ij
    0.08
     smoothly
    0.08
    (loc
    0.07
    å±Ģéĥ¨çļĦ
    0.07
     local
    0.07
    loc
    0.07
    Activations Density 0.013%

    No Known Activations