© 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. 46649
    Prev
    Next
    INDEX
    Explanations

    External links

    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
    reso
    -0.12
    stras
    -0.11
    strand
    -0.10
    iez
    -0.10
    Synopsis
    -0.10
    mpr
    -0.10
     eid
    -0.10
    elin
    -0.10
    otta
    -0.10
     oppon
    -0.10
    POSITIVE LOGITS
     External
    0.20
    External
    0.20
     external
    0.15
    References
    0.14
     References
    0.13
     Related
    0.12
     Foot
    0.11
    external
    0.11
     foot
    0.10
     Links
    0.10
    Activations Density 0.725%

    No Known Activations