© 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. 48452
    Prev
    Next
    INDEX
    Explanations

    predicament

    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
    aris
    -0.09
    pyx
    -0.08
     Ling
    -0.08
    atos
    -0.08
     settle
    -0.08
     pi
    -0.08
     ide
    -0.08
    fsp
    -0.08
     ideally
    -0.08
    ella
    -0.08
    POSITIVE LOGITS
    naires
    0.10
    orsk
    0.10
    abei
    0.10
     Franken
    0.10
    ged
    0.09
    uple
    0.09
    738
    0.09
     gag
    0.09
     mez
    0.09
    ech
    0.09
    Activations Density 0.001%

    No Known Activations