© 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. 14360
    Prev
    Next
    INDEX
    Explanations

    say "con"

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

    No Comments

    Negative Logits
    TickCount
    -16.25
    iap
    -15.88
    inspace
    -15.38
    stück
    -15.38
     fingert
    -15.06
    _Stream
    -14.38
    iado
    -14.31
    rips
    -14.19
    浞
    -14.13
     darn
    -14.06
    POSITIVE LOGITS
    cone
    24.38
    -Con
    23.25
    con
    22.25
    _conv
    21.38
     Con
    21.25
    .con
    20.75
    -con
    20.75
     con
    20.75
    conv
    20.25
    _con
    20.13
    Activations Density 0.471%

    No Known Activations