© 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. 2934
    Prev
    Next
    INDEX
    Explanations

    say mutation

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

    No Comments

    Negative Logits
     Ver
    -30.13
    Ver
    -30.00
    (ver
    -29.50
    .ver
    -29.13
    _ver
    -28.25
    -ver
    -28.25
    ver
    -27.88
    .Ver
    -25.75
     ver
    -25.13
    =config
    -21.38
    POSITIVE LOGITS
     Kaplan
    16.13
     mutants
    15.50
    validation
    15.31
     mutation
    15.13
     mechan
    15.00
     mutant
    14.69
    驻
    14.63
     patient
    14.31
     validation
    14.19
    agn
    14.00
    Activations Density 0.051%

    No Known Activations