© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 289
    Prev
    Next
    INDEX
    Explanations

    say capital letter pairs

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

    No Comments

    Negative Logits
    .nlm
    -15.56
     scp
    -14.69
    _BITS
    -14.50
    gmt
    -14.44
    .tpl
    -14.31
    .ibm
    -14.13
    scp
    -13.88
     mpfr
    -13.38
    cca
    -13.25
    slt
    -13.19
    POSITIVE LOGITS
     SB
    44.50
     MG
    43.50
     TC
    43.00
     TB
    42.50
     FS
    42.50
     HB
    42.25
     TG
    42.25
     CB
    42.25
     DG
    41.75
     MH
    41.50
    Activations Density 0.815%

    No Known Activations