© 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. 2281
    Prev
    Next
    INDEX
    Explanations

    say hus

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

    No Comments

    Negative Logits
    定
    -20.13
     Ant
    -17.63
    =obj
    -17.13
    amines
    -16.25
    iamond
    -15.88
    Ant
    -15.88
     ant
    -15.06
    矿区
    -14.88
     Cocktail
    -14.75
    idge
    -14.63
    POSITIVE LOGITS
     Hus
    50.75
     hus
    34.25
    hus
    28.75
     Hyp
    25.50
     Hut
    23.63
     hyp
    23.50
     hut
    22.50
     hypotheses
    21.13
     hypothesis
    20.75
    hyp
    20.63
    Activations Density 0.014%

    No Known Activations