© 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. 32319
    Prev
    Next
    INDEX
    Explanations

    adjustable components and features

    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
    opro
    -0.11
     Hayden
    -0.10
    jur
    -0.10
     Cath
    -0.10
     induced
    -0.10
    103
    -0.10
     avent
    -0.10
     Ahead
    -0.09
    wend
    -0.09
    -addon
    -0.09
    POSITIVE LOGITS
     accommodate
    0.13
     accommodating
    0.12
     accommod
    0.12
    /custom
    0.12
     via
    0.11
     widths
    0.11
    izable
    0.11
     customizable
    0.10
     accom
    0.10
    able
    0.10
    Activations Density 0.256%

    No Known Activations