© 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. 16820
    Prev
    Next
    INDEX
    Explanations

    efforts, implementation, steps taken

    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
     prolong
    -0.12
     uncont
    -0.09
    agos
    -0.09
     Baxter
    -0.09
    qui
    -0.09
    .Settings
    -0.09
    rup
    -0.09
     prolonged
    -0.09
     quicker
    -0.08
     dood
    -0.08
    POSITIVE LOGITS
    /how
    0.12
     each
    0.11
     exact
    0.11
     specifics
    0.10
     etc
    0.10
    —which
    0.10
    each
    0.10
     lest
    0.10
    aut
    0.10
    oad
    0.10
    Activations Density 0.301%

    No Known Activations