© 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. 2256
    Prev
    Next
    INDEX
    Explanations

    say 孟

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

    No Comments

    Negative Logits
    .dev
    -17.25
    elong
    -16.25
     deviation
    -15.81
    vis
    -15.44
    peg
    -15.31
    hx
    -15.25
     stunt
    -15.13
     eq
    -14.81
    STONE
    -14.63
    poly
    -14.56
    POSITIVE LOGITS
    孟
    80.50
     Str
    70.00
    Str
    69.50
    str
    68.50
     str
    67.50
    -str
    64.50
    .str
    62.50
    (str
    61.75
    ,str
    61.50
    	str
    60.00
    Activations Density 0.041%

    No Known Activations