© 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. 90432
    Prev
    Next
    INDEX
    Explanations

    early historical terms

    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
     pros
    -0.11
     cherry
    -0.10
     whole
    -0.10
     thought
    -0.10
     ones
    -0.10
    âĢ¦the
    -0.10
     truth
    -0.09
    igli
    -0.09
    âĢ¦it
    -0.09
     operative
    -0.09
    POSITIVE LOGITS
    ories
    0.14
     earliest
    0.14
    oretical
    0.13
    odor
    0.13
     term
    0.12
     oldest
    0.11
    odore
    0.11
    esta
    0.10
     decline
    0.10
    ACP
    0.10
    Activations Density 0.935%

    No Known Activations