© 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. 113929
    Prev
    Next
    INDEX
    Explanations

    two or multiple items

    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
    intl
    -0.10
     Letters
    -0.10
     бÑĥд
    -0.10
     exempl
    -0.09
    sch
    -0.09
    émon
    -0.09
     Carpenter
    -0.09
     fingers
    -0.09
     circumstance
    -0.09
    lider
    -0.09
    POSITIVE LOGITS
     sets
    0.12
     redund
    0.12
    /th
    0.10
    sets
    0.10
     Sets
    0.09
    Sets
    0.09
     simultaneous
    0.09
    bows
    0.09
     umb
    0.08
     passports
    0.08
    Activations Density 0.821%

    No Known Activations