© 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. 14846
    Prev
    Next
    INDEX
    Explanations

    operation names

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

    No Comments

    Negative Logits
    �
    -16.38
    ник
    -16.00
    |;↵
    -15.63
    |h
    -15.13
    |{↵
    -15.00
    驴
    -15.00
    óm
    -14.88
    ldr
    -14.81
    珠
    -14.81
    qed
    -14.75
    POSITIVE LOGITS
     slam
    16.25
     Di
    15.69
     closure
    15.06
    _PRI
    14.88
    CLOSE
    14.50
    amy
    14.44
    RIORITY
    14.19
    Di
    14.13
    emony
    13.75
    apo
    13.50
    Activations Density 0.003%

    No Known Activations