© 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. 48320
    Prev
    Next
    INDEX
    Explanations

    degree or likelihood

    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
    led
    -0.11
     quite
    -0.11
     Entire
    -0.10
    Anywhere
    -0.10
     Prefer
    -0.10
    Unhandled
    -0.09
     insufficient
    -0.09
    isan
    -0.09
     nowhere
    -0.09
    affles
    -0.09
    POSITIVE LOGITS
     likelihood
    0.15
     chances
    0.13
     chance
    0.13
     lik
    0.13
     likely
    0.12
     easily
    0.12
     eas
    0.11
     readily
    0.11
     willingness
    0.10
    /if
    0.10
    Activations Density 0.146%

    No Known Activations