© 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. 332
    Prev
    Next
    INDEX
    Explanations

    Tamil script

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

    No Comments

    Negative Logits
    徽
    -16.88
    SW
    -16.38
    糁
    -15.19
    弋
    -14.94
    昴
    -14.94
    (IC
    -14.88
    (mb
    -14.44
    SB
    -13.50
    昺
    -13.44
     afr
    -13.31
    POSITIVE LOGITS
     TA
    56.50
     TD
    55.25
     TB
    52.50
    TD
    51.25
     TC
    50.50
     TP
    50.25
     TN
    49.75
    (td
    49.75
    TA
    49.00
     TS
    48.50
    Activations Density 1.472%

    No Known Activations