© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14355
    Prev
    Next
    INDEX
    Explanations

    say 1

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

    No Comments

    Negative Logits
    jem
    -19.50
    SH
    -18.63
    ushi
    -18.38
    shm
    -18.13
    igator
    -18.13
    Rp
    -17.00
    uit
    -16.75
    xia
    -16.75
    resh
    -16.63
    jmp
    -16.63
    POSITIVE LOGITS
     candle
    18.50
    箫
    15.81
     Beverly
    14.69
     candles
    14.63
    pol
    14.44
    -pol
    14.38
     Pike
    14.25
    iland
    14.06
     Candle
    14.06
     endure
    14.06
    Activations Density 0.031%

    No Known Activations