© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 608
    Prev
    Next
    INDEX
    Explanations

    say "IM" tokens

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

    No Comments

    Negative Logits
     Louisiana
    -25.38
    湖北
    -24.75
    湖北省
    -24.13
     NL
    -23.50
    蕲
    -23.13
     louis
    -23.00
     Holland
    -22.75
     texas
    -22.63
     Texas
    -20.75
     Belgium
    -20.75
    POSITIVE LOGITS
     IM
    44.50
    IM
    42.25
    (IM
    37.50
    <IM
    36.50
    .IM
    34.00
     IMF
    30.63
    _IM
    30.25
     IMD
    29.25
     CIM
    28.75
    IMS
    25.00
    Activations Density 0.115%

    No Known Activations