© 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. 14928
    Prev
    Next
    INDEX
    Explanations

    say "non‑ASCII words"

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

    No Comments

    Negative Logits
    Ĥ
    -17.00
    ivan
    -16.38
    𝐻
    -16.13
    conv
    -15.69
     Haw
    -15.25
     hyp
    -15.13
    HH
    -14.75
     Howell
    -14.63
     humor
    -14.50
    HW
    -14.50
    POSITIVE LOGITS
    Grün
    19.25
    琅
    17.88
     Ranger
    17.25
     Ки
    17.00
     Köln
    16.88
    郎
    16.75
     ROAD
    16.75
    alle
    16.25
    AIN
    16.13
    oine
    16.13
    Activations Density 0.678%

    No Known Activations