© 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. 15035
    Prev
    Next
    INDEX
    Explanations

    username

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

    No Comments

    Negative Logits
    appen
    -18.88
     Phelps
    -18.75
    amarin
    -18.75
    .SendMessage
    -18.38
    ENDOR
    -18.00
    �示
    -17.75
    发文
    -17.63
     nâ
    -17.38
    賞
    -17.00
    ooting
    -16.88
    POSITIVE LOGITS
    EZ
    14.94
    G
    14.50
    asz
    13.69
    mq
    13.50
    ertz
    13.44
    玥
    13.44
    kel
    13.31
     Ez
    13.19
    Greg
    13.06
     ecl
    13.00
    Activations Density 0.015%

    No Known Activations