© 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. 5591
    Prev
    Next
    INDEX
    Explanations

    References and notes sections

    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
    freeze
    -0.10
    prot
    -0.10
    Wer
    -0.09
    pha
    -0.09
     sauna
    -0.09
    ëĭ
    -0.09
    cosa
    -0.09
    pg
    -0.09
    iban
    -0.09
    Pix
    -0.09
    POSITIVE LOGITS
     imports
    0.10
     Grat
    0.09
     imported
    0.09
    áº
    0.09
    conversation
    0.09
     goods
    0.08
    ubit
    0.08
     convo
    0.08
     Sens
    0.08
     Moreno
    0.08
    Activations Density 0.014%

    No Known Activations