© 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. 14595
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     Hans
    -21.88
    -h
    -20.13
    贺
    -19.00
    _h
    -18.75
    éric
    -18.38
    ónica
    -17.88
    :h
    -17.63
    ｈ
    -17.50
    h
    -17.00
     hinge
    -17.00
    POSITIVE LOGITS
     vf
    15.75
     Virgin
    15.31
     Marl
    14.94
     Slut
    14.81
    vf
    14.63
     shovel
    14.38
    agas
    14.19
     deser
    14.13
     Shields
    14.13
     charity
    13.94
    Activations Density 0.139%

    No Known Activations