© 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. 91744
    Prev
    Next
    INDEX
    Explanations

    simple, simpler, or simple-like descriptions

    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
     masculine
    -0.11
     male
    -0.11
     Male
    -0.11
    _male
    -0.11
     feminine
    -0.10
     female
    -0.10
     Female
    -0.10
     masculinity
    -0.10
     tend
    -0.10
     femin
    -0.10
    POSITIVE LOGITS
     simpler
    0.12
     SIMPLE
    0.11
     Exped
    0.10
     Strange
    0.10
     simples
    0.10
    -simple
    0.10
     simple
    0.10
     insensitive
    0.10
     creatures
    0.10
     oblivious
    0.10
    Activations Density 0.070%

    No Known Activations