© 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. 5754
    Prev
    Next
    INDEX
    Explanations

    political party, month, war, outcomes

    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
     [âĢ¦]↵↵
    -0.17
     [âĢ¦
    -0.13
     [âĢ¦]
    -0.11
    [âĢ¦]
    -0.11
    “.
    -0.10
     [...]↵↵
    -0.10
    –↵↵
    -0.10
     Laf
    -0.10
    izza
    -0.10
    âĢ¦.↵↵
    -0.09
    POSITIVE LOGITS
     ect
    0.12
     bye
    0.11
     aprove
    0.10
    !!↵
    0.10
     unt
    0.09
     id
    0.09
    /is
    0.09
     prob
    0.09
    UG
    0.08
    ~↵
    0.08
    Activations Density 0.399%

    No Known Activations