© 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. 15930
    Prev
    Next
    INDEX
    Explanations

    [vari] => [ous]

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

    No Comments

    Negative Logits
     PAC
    -30.38
     Wak
    -30.25
     Lac
    -29.00
     Baker
    -28.63
    aco
    -28.50
    lake
    -28.00
     Rach
    -28.00
     Lak
    -27.63
     Eck
    -27.25
     Shack
    -27.13
    POSITIVE LOGITS
    仡
    21.00
     Lowell
    21.00
    琉
    20.38
     Luz
    20.25
    申博
    19.88
    anth
    19.75
    鞠
    19.25
    筠
    18.88
     Lilly
    18.88
    iod
    18.75
    Activations Density 7.163%

    No Known Activations