© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1302
    Prev
    Next
    INDEX
    Explanations

    [teaching] => [teaching]

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

    No Comments

    Negative Logits
     teaching
    -48.25
     Teaching
    -46.75
    Te
    -45.25
    教学
    -43.25
     teach
    -42.25
     Teach
    -42.25
     Te
    -42.00
     TE
    -41.75
    -te
    -40.50
     teas
    -37.75
    POSITIVE LOGITS
    carbon
    17.50
     Sym
    17.00
     Carbon
    16.63
    材料
    16.63
     carbon
    16.63
    onis
    16.63
    angelo
    16.13
    Sym
    15.56
     material
    15.50
    Carbon
    15.44
    Activations Density 0.103%

    No Known Activations