© 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. 5763
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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
    adro
    -0.12
    stre
    -0.11
    oper
    -0.11
    à¸Ķ
    -0.11
    MIC
    -0.11
     Kro
    -0.10
    igel
    -0.10
    ifest
    -0.10
    ymmetric
    -0.10
     wound
    -0.10
    POSITIVE LOGITS
     stocking
    0.10
    uta
    0.09
    -close
    0.09
     review
    0.09
     stocked
    0.08
     aut
    0.08
    awe
    0.08
     stacked
    0.08
    ocr
    0.08
     product
    0.08
    Activations Density 0.003%

    No Known Activations