© 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. 15325
    Prev
    Next
    INDEX
    Explanations

    numbers

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

    No Comments

    Negative Logits
    прос
    -19.75
    orman
    -16.13
    视
    -15.88
    reas
    -15.81
    roach
    -15.75
    (Void
    -15.75
    ersed
    -15.50
     Roch
    -15.19
    erto
    -15.13
    �
    -15.06
    POSITIVE LOGITS
    kbd
    17.63
     filler
    16.50
    ldb
    16.13
     NDP
    15.38
    ugg
    14.88
    mpl
    14.88
     cú
    14.88
    odb
    14.75
    kJ
    14.63
    ky
    14.50
    Activations Density 0.098%

    No Known Activations