© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2827
    Prev
    Next
    INDEX
    Explanations

    say hyp

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

    No Comments

    Negative Logits
     Str
    -21.00
    发
    -19.75
    .str
    -17.75
    hog
    -17.25
     comm
    -17.13
    Str
    -17.00
    amento
    -16.50
     str
    -16.38
    (Str
    -16.13
    ipation
    -15.75
    POSITIVE LOGITS
     Hyp
    64.00
     hyp
    61.50
    hyp
    60.00
     hypothesis
    58.50
     hypotheses
    50.75
     hypo
    42.50
     hypers
    39.75
     hyper
    39.25
    hyper
    39.25
    Hyper
    37.75
    Activations Density 0.071%

    No Known Activations