© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1255
    Prev
    Next
    INDEX
    Explanations

    [ham] => [hamstrings]

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

    No Comments

    Negative Logits
    SM
    -28.25
    GM
    -27.63
    TM
    -26.75
     FM
    -26.50
     SM
    -25.88
    OM
    -25.25
     GM
    -25.25
    ROM
    -25.13
    VM
    -25.00
    _SM
    -24.75
    POSITIVE LOGITS
     arp
    14.94
    甲
    14.00
    刑警
    13.69
     SQL
    13.69
     Apple
    13.63
    ろう
    13.56
    インタ
    13.44
    _BUFF
    13.38
    gone
    13.25
    工地
    13.19
    Activations Density 0.807%

    No Known Activations