© 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. 14579
    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
     P
    -19.50
    P
    -19.13
    zer
    -18.63
    _p
    -18.50
     p
    -18.25
     Pere
    -18.13
    jer
    -17.25
     diner
    -17.13
    htable
    -16.88
    -p
    -16.75
    POSITIVE LOGITS
     tipped
    17.00
    cbd
    16.63
    regs
    16.63
    cats
    16.50
    -car
    15.81
    ROP
    15.63
    秋冬
    15.50
    羰
    15.50
    quat
    15.44
    caps
    15.31
    Activations Density 0.619%

    No Known Activations