© 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. 15151
    Prev
    Next
    INDEX
    Explanations

    say "female names"

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

    No Comments

    Negative Logits
    SCI
    -17.88
    инг
    -16.63
    �单
    -16.63
    VR
    -16.13
    PCM
    -16.00
    CTR
    -15.75
    _SF
    -15.56
     бил
    -15.31
    ICI
    -15.13
    IBC
    -15.13
    POSITIVE LOGITS
    lotte
    15.75
     Turner
    15.19
    嫂
    15.06
    蓉
    15.00
     Louise
    13.88
    eve
    13.81
    妹子
    13.81
    Anne
    13.44
    ellar
    13.31
    kke
    13.31
    Activations Density 0.048%

    No Known Activations