© 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. 2927
    Prev
    Next
    INDEX
    Explanations

    say "vertical"

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

    No Comments

    Negative Logits
     pres
    -17.88
     genotype
    -17.13
     regime
    -15.50
    洪
    -15.38
    (cache
    -15.25
     Cmd
    -15.00
    SEN
    -15.00
     volunt
    -14.56
    /gen
    -14.56
    pres
    -14.44
    POSITIVE LOGITS
    垂直
    36.75
    Vert
    35.25
     vert
    34.25
     Vert
    31.75
    _vert
    30.75
     ver
    30.50
     Ver
    29.13
    vert
    28.38
    (ver
    27.63
    Ver
    26.88
    Activations Density 0.069%

    No Known Activations