© 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. 15706
    Prev
    Next
    INDEX
    Explanations

    [option] => [next option]

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

    No Comments

    Negative Logits
    ಡ
    -15.44
    utton
    -15.25
    }@
    -14.81
     dela
    -14.44
    ippet
    -14.00
    arrays
    -13.88
    elize
    -13.75
    чу
    -13.75
    ania
    -13.63
    _ARRAY
    -13.63
    POSITIVE LOGITS
    crime
    25.38
     Porn
    24.25
     crime
    22.75
     pornography
    22.75
     sports
    22.50
     gamers
    22.13
     parents
    21.75
     Football
    21.50
     musicians
    21.50
    porn
    21.25
    Activations Density 0.586%

    No Known Activations