© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 16468
    Prev
    Next
    INDEX
    Explanations

    Cbd oil, treatment, biology, medicine

    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
    —not
    -0.10
    —one
    -0.09
    —we
    -0.09
    —
    -0.09
     Re
    -0.09
    —a
    -0.09
    —in
    -0.08
    ---
    -0.08
    ente
    -0.08
    —it
    -0.08
    POSITIVE LOGITS
     —↵↵
    0.19
     —
    0.19
     meds
    0.14
     bigger
    0.14
     pillar
    0.13
     cured
    0.13
     --↵
    0.12
     --↵↵
    0.11
     lasting
    0.11
     pill
    0.11
    Activations Density 0.020%

    No Known Activations