© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14790
    Prev
    Next
    INDEX
    Explanations

    say "6"

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

    No Comments

    Negative Logits
    鳅
    -18.63
    icode
    -16.63
    ivos
    -16.38
    idf
    -16.38
    isoft
    -16.25
    uchos
    -16.25
    ido
    -16.00
    izr
    -15.94
    qid
    -15.94
    anship
    -15.88
    POSITIVE LOGITS
    brace
    17.25
    emm
    15.69
    噍
    15.00
    omens
    13.69
    kräfte
    13.63
    ê
    13.56
    argc
    13.50
    e
    13.06
    -MM
    12.81
    amel
    12.75
    Activations Density 0.020%

    No Known Activations