© 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. 2268
    Prev
    Next
    INDEX
    Explanations

    say fil

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

    No Comments

    Negative Logits
    (gen
    -18.00
     reg
    -17.50
     Inc
    -17.00
    Gen
    -16.63
    (Msg
    -16.00
     Gen
    -15.94
     million
    -15.50
    -inc
    -15.38
     Thousand
    -14.75
    posé
    -14.75
    POSITIVE LOGITS
     fil
    53.00
     Fil
    50.25
    Fil
    47.00
    (fil
    46.50
    fil
    45.00
    .fil
    44.00
    _fil
    43.25
     FIL
    41.00
     filament
    36.50
    滤
    35.00
    Activations Density 0.025%

    No Known Activations