© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114883
    Prev
    Next
    INDEX
    Explanations

    intensity and modes

    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
     influ
    -0.10
    Pages
    -0.09
    ’B
    -0.09
    erals
    -0.09
     Ones
    -0.09
    Contents
    -0.09
     Bernard
    -0.09
     ctor
    -0.08
     Hope
    -0.08
    iten
    -0.08
    POSITIVE LOGITS
     styles
    0.13
     intensity
    0.13
     patterns
    0.12
     pattern
    0.12
     style
    0.12
     modes
    0.12
     options
    0.11
     Styles
    0.11
     mode
    0.11
     strength
    0.11
    Activations Density 0.031%

    No Known Activations