© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    say tabs

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

    No Comments

    Negative Logits
     ser
    -16.38
    vec
    -16.13
     col
    -16.13
    	col
    -16.00
    袋
    -15.75
     Arr
    -15.69
     genera
    -15.63
    phen
    -15.63
     membr
    -15.50
    arr
    -15.44
    POSITIVE LOGITS
     tabs
    20.88
    _tabs
    18.25
     digit
    17.88
    .tabs
    17.50
    _tab
    17.38
    Tabs
    17.25
    终端
    17.00
    ngth
    16.50
     Digit
    16.38
    淦
    16.38
    Activations Density 0.011%

    No Known Activations