© 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. 31247
    Prev
    Next
    INDEX
    Explanations

    Copyright statements and licensing

    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
     ing
    -0.11
    Âł
    -0.10
     Hus
    -0.10
    iro
    -0.09
     extraordin
    -0.08
    oval
    -0.08
     Consortium
    -0.08
    */,
    -0.08
     ingest
    -0.08
    aste
    -0.08
    POSITIVE LOGITS
     cob
    0.11
     noqa
    0.11
    ensch
    0.09
    lle
    0.09
     privile
    0.09
    nda
    0.09
     Compound
    0.09
     initiator
    0.09
     Transparent
    0.08
    yll
    0.08
    Activations Density 0.383%

    No Known Activations