© 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. 116688
    Prev
    Next
    INDEX
    Explanations

    so the

    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
    Ãł
    -0.10
     OTHERWISE
    -0.10
    THEN
    -0.10
     Duch
    -0.10
     THEN
    -0.10
     Obl
    -0.10
    obl
    -0.10
    iez
    -0.10
    odash
    -0.10
    .tbl
    -0.09
    POSITIVE LOGITS
     if
    0.13
     feel
    0.12
     whichever
    0.11
     expect
    0.10
     thankfully
    0.10
    Feel
    0.09
     chances
    0.09
     whether
    0.09
     although
    0.09
     Feel
    0.09
    Activations Density 0.046%

    No Known Activations