© 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. 115856
    Prev
    Next
    INDEX
    Explanations

    section headers like {#xxxx-sec-xxxx}

    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
    -Allow
    -0.10
     Spawn
    -0.10
    fair
    -0.10
     Ranked
    -0.10
    etz
    -0.09
    (hw
    -0.09
    za
    -0.09
    eko
    -0.09
     Broadcast
    -0.09
     [].
    -0.09
    POSITIVE LOGITS
     readers
    0.11
     Readers
    0.09
     lest
    0.09
     FAQ
    0.08
     reader
    0.08
    reader
    0.08
    odox
    0.08
     Zig
    0.08
     intric
    0.08
     disse
    0.08
    Activations Density 0.003%

    No Known Activations