© 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. 15965
    Prev
    Next
    INDEX
    Explanations

    say Chinese characters

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

    No Comments

    Negative Logits
    (fm
    -39.25
    (pm
    -39.25
    bm
    -36.75
    RAM
    -36.25
     PM
    -36.25
     xm
    -36.00
    	pm
    -36.00
     BM
    -36.00
    ram
    -35.00
    BM
    -35.00
    POSITIVE LOGITS
    隍
    18.75
    狐
    18.00
    苫
    17.50
    揪
    17.13
    弋
    16.88
    珐
    16.50
     Lac
    15.94
    窖
    15.63
    轲
    15.50
    碟
    15.44
    Activations Density 4.761%

    No Known Activations