© 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. 16319
    Prev
    Next
    INDEX
    Explanations

    say "index"

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

    No Comments

    Negative Logits
     ears
    -17.50
    MediaType
    -17.25
    耳朵
    -15.50
    背
    -15.38
    nodeName
    -15.19
     trans
    -15.13
     Bret
    -14.88
     manufactures
    -14.88
    queeze
    -14.81
     Calif
    -14.69
    POSITIVE LOGITS
     index
    47.25
     Index
    45.25
    index
    44.25
     indexes
    42.00
    Index
    41.75
    _index
    40.50
     indices
    40.00
     indexing
    39.50
     INDEX
    39.00
    索
    38.75
    Activations Density 0.198%

    No Known Activations