© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17510
    Prev
    Next
    INDEX
    Explanations

    origins of humanity

    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
     pity
    -0.09
     intervening
    -0.09
     sponsored
    -0.09
     interim
    -0.09
    /sign
    -0.09
    lies
    -0.09
     sponsor
    -0.08
     Dort
    -0.08
     Berm
    -0.08
     Cody
    -0.08
    POSITIVE LOGITS
     cav
    0.14
     mankind
    0.14
     civilization
    0.12
     recorded
    0.12
     dawn
    0.12
     Lazar
    0.12
     caves
    0.11
     existence
    0.11
     humans
    0.11
    ako
    0.11
    Activations Density 0.142%

    No Known Activations