© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15925
    Prev
    Next
    INDEX
    Explanations

    say "ક"

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

    No Comments

    Negative Logits
    -l
    -42.50
    LC
    -40.25
     LM
    -39.25
    _lc
    -39.00
    LP
    -38.75
     LP
    -38.75
     lf
    -38.75
    (ld
    -38.75
     lx
    -38.75
     LD
    -38.50
    POSITIVE LOGITS
    nels
    16.13
    滚
    15.56
    抟
    15.31
    adel
    15.19
    饽
    14.38
    丸
    14.06
    舛
    14.00
     bubb
    13.69
     cereal
    13.56
    -Col
    13.31
    Activations Density 4.343%

    No Known Activations