© 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. 89894
    Prev
    Next
    INDEX
    Explanations

    places and destinations

    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
     downstairs
    -0.12
    iesen
    -0.10
     everywhere
    -0.10
     upstairs
    -0.09
     stray
    -0.09
     comparative
    -0.09
     Impress
    -0.09
     elsewhere
    -0.09
     downhill
    -0.09
     Comparative
    -0.09
    POSITIVE LOGITS
     for
    0.16
     to
    0.15
     untuk
    0.14
    for
    0.13
     длÑı
    0.13
     accompanied
    0.11
     early
    0.11
     unarmed
    0.10
     seeking
    0.10
     Äijá»ĥ
    0.10
    Activations Density 0.149%

    No Known Activations