© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16066
    Prev
    Next
    INDEX
    Explanations

    say rubber

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

    No Comments

    Negative Logits
     Pratt
    -21.00
     Prescott
    -20.25
    rike
    -19.25
     Olson
    -18.88
    PRE
    -18.75
     Perkins
    -18.63
    邸
    -18.25
    -pre
    -18.13
    _prec
    -17.88
    midt
    -17.75
    POSITIVE LOGITS
     rubber
    21.63
    毒性
    21.38
     Rubber
    20.25
    兰花
    20.00
    橡胶
    17.75
    粘
    17.13
     cigar
    17.00
    染
    16.88
    牙
    16.75
    咬
    16.75
    Activations Density 1.346%

    No Known Activations