© 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. 19446
    Prev
    Next
    INDEX
    Explanations

    kinds of, or tends to

    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
    andalone
    -0.07
     corrup
    -0.07
    æĩĤçļĦ
    -0.06
    sic
    -0.06
     ÙĨظÙħ
    -0.06
    åIJįåŃĹåı«
    -0.06
     standalone
    -0.06
    utor
    -0.06
    asco
    -0.06
    ä»ĸ们认为
    -0.06
    POSITIVE LOGITS
     perhaps
    0.08
     nevertheless
    0.08
     admittedly
    0.08
    (cf
    0.08
    —at
    0.07
    perhaps
    0.07
    èĩ³å°ij
    0.07
    并æī¿æĭħ
    0.07
     nonetheless
    0.07
    öll
    0.07
    Activations Density 0.376%

    No Known Activations