© 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. 14784
    Prev
    Next
    INDEX
    Explanations

    say "acronyms"

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

    No Comments

    Negative Logits
    entine
    -22.38
    ennon
    -21.63
    Pen
    -21.25
    ensen
    -20.63
    rin
    -20.38
    enet
    -20.25
    _pen
    -20.25
    stdin
    -19.88
    ën
    -19.75
    nen
    -19.50
    POSITIVE LOGITS
    abort
    14.56
    �
    14.19
    íf
    14.13
    相遇
    14.00
    滴
    14.00
    족
    13.63
    ตรา
    13.50
    iage
    13.50
    er
    13.31
     slugg
    13.19
    Activations Density 0.163%

    No Known Activations