© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15809
    Prev
    Next
    INDEX
    Explanations

    say "cl"

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

    No Comments

    Negative Logits
     Levi
    -22.00
    .rpm
    -21.88
     Peb
    -21.50
    脱发
    -21.00
     Nissan
    -20.88
     coch
    -20.00
    蛔
    -19.88
     plut
    -19.75
    eph
    -19.75
     Carson
    -19.63
    POSITIVE LOGITS
     Brooke
    24.38
     Luk
    22.25
     Eleanor
    21.63
    .Cl
    18.88
     Cl
    18.88
     Westbrook
    18.75
    _cl
    18.25
     Jame
    18.25
    _Cl
    18.25
     cl
    18.13
    Activations Density 3.976%

    No Known Activations