© 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. 27206
    Prev
    Next
    INDEX
    Explanations

    fight or struggle

    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
     battlefield
    -0.12
     unprotected
    -0.11
     undef
    -0.10
     Wend
    -0.10
     Battlefield
    -0.09
     Ping
    -0.09
     Haus
    -0.09
     whistle
    -0.09
     graceful
    -0.09
     Bert
    -0.09
    POSITIVE LOGITS
     harder
    0.10
     Middleton
    0.10
     inevitable
    0.10
     unequal
    0.10
    412
    0.10
    Trivia
    0.10
     capture
    0.10
     hardest
    0.09
    alis
    0.09
     fate
    0.09
    Activations Density 0.005%

    No Known Activations