© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15529
    Prev
    Next
    INDEX
    Explanations

    say bias

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

    No Comments

    Negative Logits
     atoms
    -18.00
    ATOM
    -17.38
    atom
    -17.13
     nuclear
    -16.63
     atom
    -16.63
    原子
    -16.13
     Atom
    -16.13
    (atom
    -15.94
    CELL
    -15.88
    anten
    -15.81
    POSITIVE LOGITS
     bias
    49.50
    Bias
    46.25
     Bias
    45.50
    偏
    44.50
    bias
    44.25
     biases
    43.50
     biased
    41.50
    _bias
    40.75
    .bias
    36.50
    biased
    34.75
    Activations Density 0.318%

    No Known Activations