© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1645
    Prev
    Next
    INDEX
    Explanations

    [小说] => [小说]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    小说
    -30.25
    小說
    -24.38
     smoke
    -22.25
    文学
    -21.75
    烟
    -21.00
     Smoke
    -19.88
    土壤
    -19.63
    文學
    -19.50
    mount
    -19.38
    holm
    -18.88
    POSITIVE LOGITS
     Angel
    16.88
    .eng
    16.38
     Jackson
    15.56
    Angel
    15.31
     angel
    15.31
     angl
    15.19
    .angular
    15.13
    oken
    15.06
     Kaw
    14.88
    Oracle
    14.75
    Activations Density 0.052%

    No Known Activations