© 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. 15850
    Prev
    Next
    INDEX
    Explanations

    say "Indic letters"

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

    No Comments

    Negative Logits
    -tr
    -66.50
     tr
    -65.50
     Tr
    -64.50
    Tr
    -63.25
    (tr
    -62.50
    tr
    -62.25
    	tr
    -61.25
    _tr
    -61.00
    -Tr
    -59.25
    .tr
    -59.00
    POSITIVE LOGITS
    �
    17.13
    芬兰
    16.13
    缂
    15.13
    portlet
    15.00
    昺
    14.94
    ങ
    14.81
    瑞典
    14.63
    ober
    14.56
    防腐
    14.25
    バル
    14.19
    Activations Density 4.529%

    No Known Activations