© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14675
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    ods
    -21.38
    shortcode
    -17.88
    ultan
    -17.50
    LinkId
    -17.25
    ırl
    -17.13
     Lodge
    -17.00
    utch
    -17.00
     Lesb
    -16.88
    loss
    -16.63
     Uzbek
    -16.38
    POSITIVE LOGITS
    aval
    15.94
    训
    15.81
    訓
    15.38
    ��
    14.44
    ia
    13.69
    BIT
    13.50
     bit
    13.25
     BIT
    13.06
    _PI
    13.00
     bits
    12.94
    Activations Density 0.028%

    No Known Activations