© 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. 14884
    Prev
    Next
    INDEX
    Explanations

    say "j" words

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

    No Comments

    Negative Logits
    Cl
    -27.38
    -cl
    -27.00
    cl
    -26.25
     Cl
    -25.75
     cl
    -24.00
    clé
    -24.00
    .cl
    -23.25
    /cl
    -23.13
    	cl
    -22.63
    _cl
    -22.50
    POSITIVE LOGITS
    贾
    18.88
    apos
    18.63
    ジャ
    18.25
    jc
    17.38
    掐
    17.00
    jay
    16.25
     Ja
    16.13
    JB
    16.00
    jal
    15.81
    Ｊ
    15.81
    Activations Density 0.563%

    No Known Activations