© 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. 14418
    Prev
    Next
    INDEX
    Explanations

    say 8

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

    No Comments

    Negative Logits
     Kitty
    -17.88
     nineteen
    -17.63
    'acc
    -16.13
     Kitt
    -16.13
     Coron
    -15.94
     Jonah
    -15.81
     nin
    -15.69
    xca
    -15.31
    cp
    -15.31
    'gc
    -15.19
    POSITIVE LOGITS
    �
    16.25
    馒头
    16.00
    尉
    16.00
     pav
    15.63
     Pillow
    15.44
    able
    15.19
    ilog
    15.06
    怃
    15.06
     valide
    15.06
    stairs
    14.63
    Activations Density 0.007%

    No Known Activations