© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16279
    Prev
    Next
    INDEX
    Explanations

    say "Harry Potter characters"

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

    No Comments

    Negative Logits
    脾气
    -16.38
    \/\/
    -15.69
    街
    -15.06
    /layouts
    -15.00
    的男人
    -14.88
    >\<
    -14.56
    的衣服
    -14.31
    大街
    -14.13
     conduc
    -14.00
    街区
    -14.00
    POSITIVE LOGITS
     phoenix
    22.75
    哈利
    22.63
     Hermione
    22.50
     TCL
    22.50
    _lm
    22.25
     LM
    22.25
     Draco
    21.75
     QS
    20.88
    UIS
    20.88
    LM
    20.88
    Activations Density 0.347%

    No Known Activations