© 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. 2502
    Prev
    Next
    INDEX
    Explanations

    say "str"

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

    No Comments

    Negative Logits
    vecs
    -16.50
     penal
    -15.06
    sap
    -14.63
    nets
    -14.50
    apos
    -14.06
    perc
    -13.94
     Nets
    -13.88
    tet
    -13.81
     Stam
    -13.63
    Perm
    -13.50
    POSITIVE LOGITS
    庄
    64.50
    str
    55.75
    Str
    54.25
     Str
    54.25
     str
    53.25
    (str
    52.25
    -str
    52.00
    STR
    50.25
    	str
    50.00
    _str
    49.50
    Activations Density 0.049%

    No Known Activations