© 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. 2234
    Prev
    Next
    INDEX
    Explanations

    polio

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

    No Comments

    Negative Logits
    红豆
    -21.50
    戒指
    -19.00
    洱
    -18.75
     cigar
    -18.63
     Gem
    -17.88
    _loan
    -17.75
    玦
    -17.75
     Arb
    -17.50
     Celt
    -17.38
    RING
    -17.38
    POSITIVE LOGITS
     pol
    16.38
    潍坊
    15.50
    ѐ
    15.44
    (builder
    15.25
    (pol
    14.94
    ocities
    14.81
    ощ
    14.69
    瘫
    14.13
    riters
    13.56
     builder
    13.44
    Activations Density 0.031%

    No Known Activations