© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14774
    Prev
    Next
    INDEX
    Explanations

    say "volcano" words

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

    No Comments

    Negative Logits
     volcan
    -18.88
     Vul
    -18.25
     vul
    -18.13
    仝
    -17.75
     Vulcan
    -17.75
     volcanic
    -17.50
     Superman
    -17.00
    羌
    -16.88
    +v
    -16.63
    钍
    -16.50
    POSITIVE LOGITS
    衔
    16.00
    ORITY
    15.44
     Winn
    15.31
    oine
    14.81
    führ
    14.56
    轸
    14.44
    衬
    14.00
    诠
    13.63
     dub
    13.56
    bil
    13.38
    Activations Density 0.027%

    No Known Activations