© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    say vowel-starting words

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

    No Comments

    Negative Logits
     Eighth
    -21.88
     eighth
    -21.00
    エ
    -20.63
    .esp
    -19.00
     ADS
    -18.75
    翁
    -18.13
     Armstrong
    -18.00
    Eight
    -17.88
    イト
    -17.88
    aqu
    -17.75
    POSITIVE LOGITS
    Lİ
    16.75
     flurry
    14.13
    рак
    13.50
    麻
    13.31
    隰
    13.31
     Di
    13.25
     di
    13.19
    FS
    13.00
    委会
    13.00
    .Commit
    12.94
    Activations Density 0.068%

    No Known Activations