© 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. 48071
    Prev
    Next
    INDEX
    Explanations

    use of this source code

    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
     pes
    -0.08
    asks
    -0.08
    arness
    -0.08
     adam
    -0.07
     carn
    -0.07
     Ware
    -0.07
    yled
    -0.07
    oci
    -0.07
     Chronicles
    -0.07
     Accord
    -0.07
    POSITIVE LOGITS
     slip
    0.10
    akan
    0.10
     bump
    0.10
     Craw
    0.09
     Pins
    0.09
    annot
    0.09
    esthes
    0.09
     Hari
    0.09
     bumps
    0.09
    cts
    0.09
    Activations Density 0.877%

    No Known Activations