© 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. 16357
    Prev
    Next
    INDEX
    Explanations

    say ze

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

    No Comments

    Negative Logits
     Abrams
    -15.31
    ings
    -15.06
    amiento
    -14.75
    ení
    -14.44
    隰
    -14.31
    ần
    -14.19
     Shirley
    -14.00
    ers
    -13.94
    lers
    -13.69
    kap
    -13.63
    POSITIVE LOGITS
    ose
    21.25
    ZE
    20.88
    lobe
    20.13
    OSE
    19.25
     bedside
    18.50
    ate
    18.25
    igate
    18.25
    yne
    17.63
     Hedge
    17.63
    olate
    17.63
    Activations Density 0.061%

    No Known Activations