© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15264
    Prev
    Next
    INDEX
    Explanations

    code line endings

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

    No Comments

    Negative Logits
    rack
    -16.25
    麻将
    -15.81
    wand
    -15.63
     Tacoma
    -15.56
    ashtra
    -15.38
     flats
    -15.38
     расход
    -15.38
    plat
    -15.31
     Idaho
    -15.25
    eus
    -15.19
    POSITIVE LOGITS
    gi
    16.88
    opher
    16.75
    因子
    15.69
    -api
    15.50
    oto
    14.63
     burial
    14.56
    keleton
    14.44
     jerk
    14.38
     bot
    14.25
    sen
    14.25
    Activations Density 0.081%

    No Known Activations