© 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. 115568
    Prev
    Next
    INDEX
    Explanations

    C, C++, code delimiters

    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
     Bain
    -0.11
     justification
    -0.10
    809
    -0.10
    ìĹ
    -0.09
     Bridges
    -0.09
     Ras
    -0.09
     Brig
    -0.09
     Briggs
    -0.09
    ei
    -0.09
     taxable
    -0.09
    POSITIVE LOGITS
    arte
    0.11
     Kab
    0.09
     Slo
    0.09
    ughs
    0.09
    ART
    0.09
     Ebony
    0.09
     separating
    0.09
    ajan
    0.08
     Fitzgerald
    0.08
    ceipt
    0.08
    Activations Density 0.001%

    No Known Activations