© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    growth or increase by a percentage

    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
     halfway
    -0.13
     Counts
    -0.11
     lowered
    -0.10
     вÑĢем
    -0.09
    etch
    -0.09
     Efficiency
    -0.09
     decreased
    -0.09
    bis
    -0.09
    ivot
    -0.09
    _fraction
    -0.09
    POSITIVE LOGITS
     growth
    0.23
     compound
    0.20
     Compound
    0.19
     Growth
    0.19
     exponential
    0.18
     explosive
    0.17
    growth
    0.17
     compounded
    0.17
    _growth
    0.16
     exploding
    0.16
    Activations Density 0.210%

    No Known Activations