© 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. 114743
    Prev
    Next
    INDEX
    Explanations

    gram, gramophone, gramicidin, gram-negative, Ukita, Ukranian

    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
    orro
    -0.11
    abee
    -0.09
    IFn
    -0.09
     Orr
    -0.09
    rio
    -0.09
     recuper
    -0.08
    irl
    -0.08
    OWL
    -0.08
     Undo
    -0.08
    uhn
    -0.08
    POSITIVE LOGITS
     Piet
    0.11
    arella
    0.10
    /to
    0.10
     savvy
    0.09
     stew
    0.09
     percept
    0.09
     grate
    0.09
     alternating
    0.09
     dam
    0.09
     enthusiastic
    0.09
    Activations Density 0.003%

    No Known Activations