© 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. 115332
    Prev
    Next
    INDEX
    Explanations

    size and characteristics

    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
    azo
    -0.09
    izu
    -0.09
     dynamically
    -0.09
    stations
    -0.09
    .sparse
    -0.08
     calmly
    -0.08
    508
    -0.08
    /debug
    -0.08
     horizontally
    -0.08
     procedure
    -0.08
    POSITIVE LOGITS
     size
    0.19
     strength
    0.14
     authenticity
    0.14
     sizes
    0.13
     Size
    0.12
     characteristics
    0.12
     quality
    0.12
     effectiveness
    0.11
     attributes
    0.11
     siz
    0.11
    Activations Density 1.423%

    No Known Activations