© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    say therm words

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

    No Comments

    Negative Logits
    宝宝
    -18.50
     regs
    -17.25
     Et
    -16.50
    etu
    -16.38
    爸爸
    -16.13
    �t
    -16.00
     Petty
    -15.88
    eton
    -15.75
    Et
    -15.63
    etal
    -15.50
    POSITIVE LOGITS
     therm
    70.50
     Therm
    62.75
    ther
    59.75
     Ther
    48.00
    汤
    46.00
     ther
    44.00
     тер
    39.25
     therapist
    36.25
    湯
    35.75
     thermo
    34.25
    Activations Density 0.054%

    No Known Activations