© 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. 2658
    Prev
    Next
    INDEX
    Explanations

    say "char"

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

    No Comments

    Negative Logits
     CAL
    -17.13
     Col
    -17.00
    (cal
    -16.88
     COL
    -16.75
    -cal
    -16.63
    -Col
    -16.63
    Col
    -15.88
    RET
    -15.75
    consult
    -15.06
    Consult
    -15.06
    POSITIVE LOGITS
     char
    42.50
     Char
    41.00
    char
    38.50
    Char
    36.25
    (char
    33.50
    ,char
    33.25
    -char
    32.00
    [char
    31.38
    	char
    29.38
    _char
    27.50
    Activations Density 0.025%

    No Known Activations