© 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. 15113
    Prev
    Next
    INDEX
    Explanations

    equals sign

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

    No Comments

    Negative Logits
    H
    -18.63
    h
    -17.63
    ect
    -17.50
     Hazel
    -17.00
     h
    -15.44
    HC
    -15.06
    هب
    -15.00
    hh
    -14.81
    HCI
    -14.63
    HT
    -14.50
    POSITIVE LOGITS
     Wilde
    17.13
    iveness
    16.50
     mar
    15.94
    关口
    15.94
    qv
    15.56
     Clarke
    15.31
    Domains
    15.19
    arl
    15.06
    qi
    14.75
     Shields
    14.75
    Activations Density 0.114%

    No Known Activations