© 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. 14970
    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
    locker
    -17.38
    Ｌ
    -15.38
    辍
    -15.31
    -lock
    -15.25
    (samples
    -15.19
    ptest
    -14.75
    enced
    -14.63
    лю
    -14.56
    óst
    -14.31
    locks
    -14.25
    POSITIVE LOGITS
    iola
    16.13
    /API
    14.63
    iya
    14.38
    Volt
    14.38
    ItemCount
    14.31
    thic
    14.13
     Gifts
    14.06
    .volume
    14.06
     Voice
    13.88
     Bened
    13.88
    Activations Density 0.011%

    No Known Activations