© 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. 0
    Prev
    Next
    INDEX
    Explanations

    say "fat" words

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

    No Comments

    Negative Logits
    蜀
    -21.00
    蟋
    -19.75
    西甲
    -18.75
    珠海
    -18.50
     Joomla
    -18.25
    滇
    -18.13
    Spot
    -18.00
     bacteria
    -17.63
     Malay
    -17.50
     Zika
    -17.38
    POSITIVE LOGITS
     fat
    18.13
    尻
    15.63
    fat
    15.13
     Fat
    15.06
    Fat
    15.06
    -fat
    14.94
    剃
    14.75
     fur
    14.06
    TAIL
    13.94
     hips
    13.75
    Activations Density 0.129%

    No Known Activations