© 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. 4584
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code formatting

    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
    cott
    -0.09
     Licensing
    -0.09
     cert
    -0.09
     Moff
    -0.09
    edd
    -0.08
     sym
    -0.08
    uo
    -0.08
     Millions
    -0.08
    vore
    -0.08
     Sour
    -0.08
    POSITIVE LOGITS
    -&
    0.09
     sortable
    0.09
    wal
    0.09
    Virgin
    0.09
     Weg
    0.09
     Umb
    0.09
     aval
    0.09
    bows
    0.09
    .Asset
    0.08
    ather
    0.08
    Activations Density 0.001%

    No Known Activations