© 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. 2800
    Prev
    Next
    INDEX
    Explanations

    say "hex"

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

    No Comments

    Negative Logits
    Recorder
    -17.50
    eras
    -17.13
    око
    -16.63
     denom
    -15.75
     Recorder
    -15.44
    Den
    -14.81
    ews
    -14.81
    eros
    -14.81
    den
    -14.75
    .aw
    -14.69
    POSITIVE LOGITS
     hex
    95.00
    hex
    88.50
     Hex
    87.00
    Hex
    86.50
    (hex
    80.50
    _hex
    80.00
     HEX
    73.00
    .hex
    71.00
    .Hex
    64.50
    _HEX
    63.00
    Activations Density 0.066%

    No Known Activations