© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14578
    Prev
    Next
    INDEX
    Explanations

    8 => 0

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

    No Comments

    Negative Logits
    àng
    -13.50
    @class
    -13.00
    @mail
    -12.38
    .bd
    -12.13
    广告
    -11.63
     posting
    -11.63
     MS
    -11.63
    adol
    -11.56
    @js
    -11.56
    @g
    -11.56
    POSITIVE LOGITS
    sse
    21.63
    ections
    21.25
    erable
    21.25
    affle
    18.50
    蔼
    18.00
    ouncer
    17.25
    ーシ
    17.13
    omm
    17.00
    ubern
    16.88
    czną
    16.88
    Activations Density 0.013%

    No Known Activations