© 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. 15074
    Prev
    Next
    INDEX
    Explanations

    say punctuation

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

    No Comments

    Negative Logits
     USPS
    -14.38
     Comcast
    -14.31
     HCI
    -13.88
    啭
    -13.50
     McDonald
    -13.19
     Cadillac
    -13.06
     Scarlett
    -12.94
     Godzilla
    -12.81
     AAC
    -12.44
     Charset
    -12.31
    POSITIVE LOGITS
    ten
    17.25
    爹
    16.88
    rev
    16.50
    тели
    16.25
    جو
    16.00
     setC
    15.94
    暫
    15.94
    ��
    15.88
    itur
    15.81
    mouth
    15.63
    Activations Density 0.454%

    No Known Activations