© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3851
    Prev
    Next
    INDEX
    Explanations

    style attribute or tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Petr
    -0.09
     scop
    -0.08
    inned
    -0.08
     Carr
    -0.08
     Hull
    -0.08
     Wise
    -0.08
    xd
    -0.07
     tot
    -0.07
    ظ
    -0.07
    dro
    -0.07
    POSITIVE LOGITS
     style
    0.73
     styles
    0.64
     Style
    0.63
    style
    0.56
    Style
    0.55
     STYLE
    0.54
     Styles
    0.52
     stylist
    0.49
    /style
    0.48
    _style
    0.46
    Activations Density 0.506%

    No Known Activations