© 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. 2672
    Prev
    Next
    INDEX
    Explanations

    say "dir"

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

    No Comments

    Negative Logits
    phen
    -18.25
    cons
    -17.75
     million
    -17.38
     Phen
    -16.63
    illion
    -16.50
    Mel
    -16.50
    万人
    -16.38
    _simulation
    -16.25
    Cons
    -16.13
    验证
    -16.13
    POSITIVE LOGITS
     dir
    60.25
    dir
    52.25
    	dir
    51.00
    .dir
    50.50
    (dir
    50.50
     Dir
    49.75
    /dir
    49.00
    Dir
    48.75
    -dir
    47.50
    [dir
    44.50
    Activations Density 0.060%

    No Known Activations