© 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. 47314
    Prev
    Next
    INDEX
    Explanations

    prefix

    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
    erdale
    -0.08
    鬣
    -0.08
     isNaN
    -0.07
    atoires
    -0.07
    adesh
    -0.07
    uarte
    -0.07
    ä¹İåħ¶
    -0.07
    atoire
    -0.07
    /host
    -0.07
    èļĵ
    -0.07
    POSITIVE LOGITS
     Prefix
    0.08
    天ä½ij
    0.07
    adies
    0.07
     unc
    0.07
     Unc
    0.07
    kie
    0.07
    æ¶ī
    0.07
     prefix
    0.07
     prefixes
    0.07
    æŁIJ
    0.07
    Activations Density 0.297%

    No Known Activations