© 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. 14903
    Prev
    Next
    INDEX
    Explanations

    say "Ch" prefix

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

    No Comments

    Negative Logits
    ras
    -20.88
    shi
    -19.63
    _rsa
    -18.13
    rice
    -17.25
    race
    -16.75
    PX
    -16.25
    rsa
    -16.25
    枕
    -16.13
    isko
    -16.00
     Rush
    -15.81
    POSITIVE LOGITS
    订
    16.13
     Weinstein
    15.31
     cloning
    15.19
    诬
    15.13
     di
    14.94
     FML
    14.81
     antid
    14.56
     Tud
    14.38
     Clone
    14.31
     clown
    14.19
    Activations Density 0.006%

    No Known Activations