© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15098
    Prev
    Next
    INDEX
    Explanations

    say "Cl"

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

    No Comments

    Negative Logits
    贾
    -19.13
    apos
    -19.13
    ジャ
    -18.25
    掐
    -17.13
    jay
    -16.75
    jc
    -16.50
    蹲
    -16.50
    jal
    -16.25
    quarters
    -15.88
    Ｊ
    -15.50
    POSITIVE LOGITS
    Cl
    26.13
    -cl
    25.50
     Cl
    24.63
    cl
    24.63
     cl
    22.63
    .cl
    22.63
    clé
    22.63
    _Cl
    21.63
    _cl
    21.50
    /cl
    21.38
    Activations Density 0.524%

    No Known Activations