© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    say "metals"

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

    No Comments

    Negative Logits
    淋巴
    -27.63
    sym
    -26.25
     lymph
    -26.25
     sym
    -24.63
     symmetry
    -23.88
    (sym
    -21.88
    Sym
    -21.38
     Symphony
    -21.13
    柳
    -21.13
     Lambert
    -21.00
    POSITIVE LOGITS
     metals
    16.88
     JSONException
    16.75
     metal
    16.13
    政策
    16.00
     Policy
    15.81
    Policy
    15.69
     policy
    15.56
    金属
    15.50
    青铜
    15.38
    铸造
    15.25
    Activations Density 0.037%

    No Known Activations