© 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. 15197
    Prev
    Next
    INDEX
    Explanations

    say "California"

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

    No Comments

    Negative Logits
    _pol
    -18.25
    -pol
    -17.13
     polynomial
    -17.00
     pol
    -16.38
    RegExp
    -16.25
    극
    -16.25
    газ
    -15.50
    Pol
    -15.50
     Polynomial
    -15.44
    rawl
    -15.19
    POSITIVE LOGITS
     Californ
    30.50
     California
    27.25
    California
    26.88
     california
    26.38
    四川省
    26.00
     Sacramento
    25.63
    四川
    25.63
     San
    25.50
     Calif
    24.88
    加州
    22.88
    Activations Density 0.390%

    No Known Activations