© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    [organ] => [substance]

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

    No Comments

    Negative Logits
     BUILD
    -17.63
    strand
    -16.88
     Build
    -16.75
     building
    -16.63
    Building
    -16.50
     Building
    -16.50
     Builds
    -16.25
    放过
    -16.25
    Build
    -16.13
    bank
    -16.00
    POSITIVE LOGITS
    上映
    15.19
    演讲
    14.19
    军事
    14.00
    口号
    13.94
    IPH
    13.88
    -shot
    13.75
     inflammatory
    13.69
    lider
    13.56
    材
    13.19
    口气
    13.19
    Activations Density 0.055%

    No Known Activations