© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14988
    Prev
    Next
    INDEX
    Explanations

    say fruit

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

    No Comments

    Negative Logits
    onica
    -20.50
    vsp
    -17.25
    烨
    -16.50
     Ashton
    -16.25
     banged
    -16.13
     ASC
    -16.13
    trs
    -15.75
    مو
    -15.13
     vans
    -15.13
    ASF
    -15.13
    POSITIVE LOGITS
    fruit
    19.88
    ora
    18.25
    杏
    18.13
     Strawberry
    17.13
    好朋友
    17.00
     Fruit
    16.63
    oral
    16.63
     FU
    16.50
    ruit
    16.38
     fruit
    16.00
    Activations Density 0.013%

    No Known Activations