© 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. 91202
    Prev
    Next
    INDEX
    Explanations

    begin / start patterns

    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
     immedi
    -0.12
    ilon
    -0.12
    atre
    -0.12
    allon
    -0.12
    spot
    -0.11
    contri
    -0.11
     proced
    -0.11
    xdb
    -0.11
    cest
    -0.11
     Slee
    -0.11
    POSITIVE LOGITS
     disillusion
    0.08
     olig
    0.08
     plast
    0.08
     likely
    0.08
     ren
    0.08
     blind
    0.08
     active
    0.07
     trivial
    0.07
     Geld
    0.07
     gia
    0.07
    Activations Density 0.025%

    No Known Activations