© 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. 46915
    Prev
    Next
    INDEX
    Explanations

    sufficiently enough

    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
     Worse
    -0.12
    Extreme
    -0.11
     bizarre
    -0.11
     unbearable
    -0.10
     questionable
    -0.10
     Extreme
    -0.10
     dismal
    -0.10
     dubious
    -0.10
     unsustainable
    -0.10
     disjoint
    -0.10
    POSITIVE LOGITS
     enough
    0.34
     Enough
    0.29
     moderate
    0.28
     moderately
    0.28
     sufficiently
    0.27
     sufficient
    0.25
     modest
    0.25
     gently
    0.24
    Enough
    0.24
     manageable
    0.23
    Activations Density 0.140%

    No Known Activations