© 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. 31271
    Prev
    Next
    INDEX
    Explanations

    more common/better part

    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
    uty
    -0.10
     Unsure
    -0.09
    aire
    -0.09
    iez
    -0.09
    oun
    -0.09
    pra
    -0.09
    IRM
    -0.09
    tro
    -0.09
    vio
    -0.09
    (fm
    -0.08
    POSITIVE LOGITS
    -than
    0.19
     aspects
    0.17
     parts
    0.13
     portions
    0.11
     among
    0.11
    among
    0.11
     ones
    0.11
     fortunate
    0.11
     moments
    0.11
    most
    0.10
    Activations Density 0.056%

    No Known Activations