© 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. 14842
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    No Comments

    Negative Logits
    stk
    -16.75
    鲂
    -15.56
     stab
    -15.25
    qp
    -15.19
    stab
    -14.75
    trl
    -14.44
     olu
    -14.38
    ulk
    -14.25
     sik
    -14.13
    berg
    -14.06
    POSITIVE LOGITS
    weed
    18.13
    immers
    17.63
    _Cl
    17.25
     Jasmine
    17.00
    粉
    16.75
    GridColumn
    16.63
    drs
    16.63
    DataSetChanged
    16.63
    Seed
    16.25
     Radiation
    16.25
    Activations Density 0.515%

    No Known Activations