© 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. 15549
    Prev
    Next
    INDEX
    Explanations

    non-ascii

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

    No Comments

    Negative Logits
    ocl
    -19.50
     Spielberg
    -18.63
     UFO
    -17.88
    UIS
    -17.75
     cliff
    -17.38
     messageId
    -16.75
    OSC
    -16.75
    汐
    -16.75
    (cl
    -16.50
    (Cl
    -16.50
    POSITIVE LOGITS
    .Primary
    16.63
    פל
    16.13
    .PR
    16.00
    _primary
    15.94
     Kerala
    15.94
    .PL
    15.44
    _Pr
    15.31
    .Pr
    15.31
     prin
    15.13
    grow
    15.00
    Activations Density 0.880%

    No Known Activations