© 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. 15267
    Prev
    Next
    INDEX
    Explanations

    paper clips, paper towels, papermaking machine

    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
    ä»ĸåij½
    -0.09
     sayıda
    -0.09
    ï¸İ
    -0.09
    ataires
    -0.08
    ampe
    -0.08
    eil
    -0.08
    ehu
    -0.08
    ëģĶ
    -0.08
    ataire
    -0.08
    ideos
    -0.08
    POSITIVE LOGITS
    istry
    0.08
    å±ij
    0.08
    antry
    0.08
    è´¨çļĦ
    0.08
    hood
    0.07
     mache
    0.07
    bag
    0.07
    crete
    0.07
    brush
    0.07
     ÑĥÑĩеÑĤа
    0.06
    Activations Density 0.056%

    No Known Activations