© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15628
    Prev
    Next
    INDEX
    Explanations

    say "ish"

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

    No Comments

    Negative Logits
    杵
    -19.25
     cue
    -18.13
    AppBundle
    -16.25
    _relations
    -15.94
    rollo
    -15.94
    悫
    -15.88
    SOLE
    -15.75
    rell
    -15.75
    竞
    -15.69
    /bit
    -15.63
    POSITIVE LOGITS
    san
    16.00
    吸烟
    14.69
    San
    14.69
    Wh
    14.56
    amar
    14.25
     San
    13.81
    nic
    13.75
    anism
    13.38
    ণ
    13.25
    car
    12.88
    Activations Density 0.000%

    No Known Activations