© 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. 14854
    Prev
    Next
    INDEX
    Explanations

    say arrow

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

    No Comments

    Negative Logits
    idal
    -20.88
    itel
    -19.38
    pac
    -19.38
    amac
    -19.25
    toc
    -18.63
    tok
    -18.63
     Gibson
    -17.75
     Zika
    -17.50
     TOK
    -17.25
    つき
    -17.25
    POSITIVE LOGITS
    浣
    18.50
    .cv
    18.50
    evt
    18.25
    anst
    18.13
    ave
    17.75
    สว
    17.50
     sant
    17.50
    _lv
    17.25
     Sew
    17.00
    antee
    16.88
    Activations Density 1.034%

    No Known Activations