© 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. 14822
    Prev
    Next
    INDEX
    Explanations

    say human

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

    No Comments

    Negative Logits
    DLL
    -18.38
    [parent
    -17.63
     RNG
    -17.38
     GSM
    -16.88
     DLL
    -16.88
    ynch
    -16.75
     �
    -16.75
    /respond
    -16.75
    規劃
    -16.75
     EDGE
    -16.63
    POSITIVE LOGITS
    人间
    14.63
    妒
    14.38
    的人
    14.31
    拉斯
    13.56
     pol
    13.38
     human
    13.13
    Them
    13.00
     bí
    12.94
    hu
    12.69
     Nietzsche
    12.56
    Activations Density 0.619%

    No Known Activations