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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15585
    Prev
    Next
    INDEX
    Explanations

    say "metal"

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

    No Comments

    Negative Logits
     jihad
    -17.13
    -interface
    -16.88
    パー
    -16.00
    iska
    -16.00
    _traj
    -16.00
    疹
    -15.88
    圌
    -15.69
    灾害
    -15.56
     subj
    -15.56
    aping
    -15.56
    POSITIVE LOGITS
    金属
    39.25
     metal
    39.25
     metals
    37.25
    铜
    35.50
     Metal
    35.50
     metallic
    33.50
    metal
    33.50
    Metal
    32.75
     metall
    32.25
     Metals
    31.88
    Activations Density 0.289%

    No Known Activations