© 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. 2954
    Prev
    Next
    INDEX
    Explanations

    say "gener"

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

    No Comments

    Negative Logits
    嫔
    -16.50
    PET
    -16.13
    (poly
    -15.13
    熔
    -15.06
     melt
    -14.94
     melts
    -14.69
    allee
    -14.44
    relay
    -14.38
     PET
    -14.38
    Tech
    -14.38
    POSITIVE LOGITS
    代
    69.50
     gener
    66.00
     Gener
    63.00
    Gener
    61.25
     gen
    59.25
     Gen
    55.50
    (gen
    54.50
    gen
    53.00
    _gener
    51.50
    gener
    51.25
    Activations Density 0.078%

    No Known Activations