© 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. 31309
    Prev
    Next
    INDEX
    Explanations

    email headers

    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
    orde
    -0.11
     Dag
    -0.10
    .svg
    -0.09
     Lew
    -0.09
    ollapsed
    -0.09
     twig
    -0.09
     UNUSED
    -0.08
     blind
    -0.08
     blat
    -0.08
    ovy
    -0.08
    POSITIVE LOGITS
     Quadr
    0.10
     sno
    0.10
     Concord
    0.09
     Wong
    0.09
    ture
    0.09
     ding
    0.08
     Cry
    0.08
     Cruise
    0.08
     Org
    0.08
     naked
    0.08
    Activations Density 0.120%

    No Known Activations