© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1700
    Prev
    Next
    INDEX
    Explanations

    say "book"

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

    No Comments

    Negative Logits
     cognitive
    -32.50
     Cognitive
    -29.13
     cognition
    -23.00
     CJ
    -22.50
    Cog
    -21.50
    ognitive
    -21.25
     CU
    -20.13
     Clover
    -20.13
     CC
    -19.75
    认知
    -19.75
    POSITIVE LOGITS
     book
    18.25
    Scripts
    16.88
     books
    16.50
    书
    16.13
    sal
    16.13
    Book
    15.38
    λ
    15.06
     SCRIPT
    14.81
     Book
    14.69
     Lindsay
    14.69
    Activations Density 0.049%

    No Known Activations