© 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. 1941
    Prev
    Next
    INDEX
    Explanations

    closest date or value

    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
    广
    -0.07
     multit
    -0.07
     Rag
    -0.07
     proto
    -0.06
    alty
    -0.06
    åĦ
    -0.06
    iddy
    -0.06
    åħļå·¥å§Ķ
    -0.06
     Basta
    -0.06
    elters
    -0.06
    POSITIVE LOGITS
     closest
    0.12
    closest
    0.11
     nearest
    0.11
     terdekat
    0.10
    nearest
    0.10
     nearby
    0.08
    .closest
    0.08
     ближай
    0.08
    éĢ¼è¿ij
    0.08
     nearer
    0.08
    Activations Density 0.026%

    No Known Activations