© 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. 15206
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
    节
    -17.75
    dna
    -16.88
     blood
    -16.00
    ston
    -15.94
    hq
    -15.38
    Blood
    -15.13
    boards
    -15.13
     Blood
    -15.06
    blood
    -14.88
    dorf
    -14.75
    POSITIVE LOGITS
     mari
    18.00
    aur
    16.88
    ェ
    16.63
     Burke
    15.81
    sparse
    15.69
    隗
    15.69
    chrome
    15.56
    omp
    15.25
     aure
    15.19
    ә
    14.81
    Activations Density 0.546%

    No Known Activations