© 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. 15159
    Prev
    Next
    INDEX
    Explanations

    numbers

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

    No Comments

    Negative Logits
     Hastings
    -16.00
    _lex
    -15.44
    枕
    -15.31
    hest
    -14.56
    泵
    -14.19
    衡
    -14.13
    ham
    -14.06
    omb
    -14.00
    IFS
    -13.94
    hy
    -13.63
    POSITIVE LOGITS
    动生成
    17.13
    恹
    16.50
    cedes
    16.38
     AOL
    16.25
    鬟
    15.81
    iska
    15.25
    然是
    15.00
     Cincinnati
    14.88
    achel
    14.75
    �
    14.75
    Activations Density 0.021%

    No Known Activations