© 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. 15308
    Prev
    Next
    INDEX
    Explanations

    early

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

    No Comments

    Negative Logits
     CONTRIBUTORS
    -16.00
     Redistributions
    -13.69
    iri
    -13.19
    比我
    -13.00
    IFI
    -12.94
    蜃
    -12.94
    牵挂
    -12.44
    估
    -12.44
    ather
    -12.25
    ests
    -12.00
    POSITIVE LOGITS
    (limit
    16.38
     hỏi
    16.25
     Disco
    16.13
    ousel
    16.00
    ramework
    15.69
     Cary
    15.69
    aval
    15.63
    earch
    15.63
    ächt
    15.31
    特派
    15.19
    Activations Density 0.040%

    No Known Activations