© 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. 6341
    Prev
    Next
    INDEX
    Explanations

    conditions and situations

    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
    itr
    -0.10
    ardi
    -0.10
    hall
    -0.10
    bern
    -0.10
     HAPP
    -0.10
     equals
    -0.10
     Dump
    -0.09
     Dal
    -0.09
    isch
    -0.09
    ictured
    -0.09
    POSITIVE LOGITS
     abound
    0.17
     suggests
    0.12
     suggest
    0.12
     tend
    0.11
     invariably
    0.11
     often
    0.11
     circulated
    0.10
     tended
    0.10
     rightly
    0.10
     reveals
    0.10
    Activations Density 1.189%

    No Known Activations