© 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. 51428
    Prev
    Next
    INDEX
    Explanations

    alcohols and derivatives

    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
    elj
    -0.07
    kite
    -0.07
    kip
    -0.06
    hawk
    -0.06
     invol
    -0.06
    asl
    -0.06
    waan
    -0.06
    笼罩
    -0.06
    æ³¢åıĬ
    -0.06
    tl
    -0.06
    POSITIVE LOGITS
    Ïģμο
    0.08
    ä¸īæ°´
    0.08
    inski
    0.08
    tober
    0.08
    çİĦå¾·
    0.07
     alcoholic
    0.07
    ç³ľ
    0.07
    à¸ķีà¸Ļ
    0.07
    ambo
    0.07
    HEY
    0.07
    Activations Density 0.036%

    No Known Activations