© 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. 397
    Prev
    Next
    INDEX
    Explanations

    [*] => 被

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

    No Comments

    Negative Logits
     DAM
    -17.75
    DMIN
    -16.88
    XML
    -16.88
     Dresden
    -16.25
    Americ
    -16.25
    ড
    -15.88
     IDR
    -15.88
    SMS
    -15.69
    uppercase
    -15.44
     Orchard
    -15.31
    POSITIVE LOGITS
    wave
    17.13
     premises
    15.94
    ways
    15.38
    垫
    15.00
    ราย
    14.75
    勃勃
    14.56
    精品
    14.25
    maal
    13.81
    AccessException
    13.69
     wave
    13.63
    Activations Density 0.044%

    No Known Activations