© 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. 15193
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    No Comments

    Negative Logits
    als
    -20.38
    icals
    -19.38
    esan
    -18.88
    alli
    -18.13
    inear
    -18.13
    reatest
    -18.00
    spender
    -17.63
    infeld
    -17.50
    icts
    -17.38
    sold
    -17.25
    POSITIVE LOGITS
     hh
    15.38
    /boot
    15.31
     mb
    15.31
    _ud
    15.25
    /mm
    15.25
     Hopkins
    15.06
     keyst
    14.69
    HO
    14.63
     vh
    14.63
    (lp
    14.56
    Activations Density 0.112%

    No Known Activations