© 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. 15052
    Prev
    Next
    INDEX
    Explanations

    say single-character tokens

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

    No Comments

    Negative Logits
    imas
    -21.00
    pei
    -20.00
    ALAR
    -19.13
    raz
    -18.50
    ernen
    -18.00
    (im
    -17.25
    ele
    -17.00
    esz
    -17.00
    ieres
    -16.75
     Emerson
    -16.50
    POSITIVE LOGITS
    -spinner
    15.94
    榖
    15.44
    ott
    14.50
    _aa
    14.25
     Antonio
    14.19
     Atlanta
    14.13
     bott
    14.13
     Corinth
    14.06
    安东尼
    14.06
    洪
    14.00
    Activations Density 0.560%

    No Known Activations