© 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. 1522
    Prev
    Next
    INDEX
    Explanations

    say Profile

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

    No Comments

    Negative Logits
     toxic
    -40.50
    有毒
    -36.00
    毒
    -36.00
     Toxic
    -35.00
     toxicity
    -35.00
     toxins
    -32.75
     toxin
    -32.25
    毒性
    -32.00
    毒素
    -31.38
     Tokens
    -29.25
    POSITIVE LOGITS
    ARG
    17.88
    _lambda
    17.00
    lambda
    17.00
    (lambda
    15.50
    arga
    15.44
     wavelength
    15.44
     lam
    15.25
    lam
    14.88
    arking
    14.25
    arbon
    13.88
    Activations Density 0.112%

    No Known Activations