© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14482
    Prev
    Next
    INDEX
    Explanations

    say "v" words

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

    No Comments

    Negative Logits
     Kad
    -18.75
     Dub
    -18.75
     claw
    -18.63
    橹
    -18.25
    car
    -18.25
    滩
    -18.25
    ija
    -18.13
     Drum
    -18.00
    棘
    -17.38
    lea
    -16.88
    POSITIVE LOGITS
    >v
    15.69
    acific
    15.38
    自愿
    15.31
    tsy
    14.75
     Virgin
    14.63
    -v
    14.56
     Volley
    14.31
    olic
    14.06
    /rfc
    14.00
    V
    13.81
    Activations Density 0.825%

    No Known Activations