© 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. 1687
    Prev
    Next
    INDEX
    Explanations

    [tumor] => [tumor]

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

    No Comments

    Negative Logits
    肿瘤
    -33.00
     tumor
    -29.63
     tumors
    -25.63
     tum
    -23.13
     cancer
    -20.13
     Cancer
    -19.25
    癌
    -19.13
    旅游业
    -19.13
    _TM
    -19.00
    Tok
    -18.13
    POSITIVE LOGITS
     interface
    18.88
    Interface
    18.75
     Interface
    18.38
     angles
    17.88
     interfaces
    17.75
     Ang
    17.63
     angle
    17.25
    Ang
    16.75
     cheese
    16.63
    aci
    16.63
    Activations Density 0.057%

    No Known Activations