© 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. 6130
    Prev
    Next
    INDEX
    Explanations

    subject to

    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
     CAS
    -0.11
     Watkins
    -0.11
    eneg
    -0.10
    ening
    -0.10
    anzi
    -0.09
     Sands
    -0.09
     Baba
    -0.09
     Went
    -0.09
     ah
    -0.09
     Haw
    -0.09
    POSITIVE LOGITS
     oper
    0.10
     inclined
    0.10
    idon
    0.09
    {*
    0.09
    ìĦ¸
    0.09
    outh
    0.08
     tal
    0.08
    emen
    0.08
    SCI
    0.08
    ioni
    0.08
    Activations Density 0.201%

    No Known Activations