© 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. 48497
    Prev
    Next
    INDEX
    Explanations

    act of, application of, helper to, refers to

    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
    NotNull
    -0.09
     basics
    -0.09
     Alta
    -0.09
     certainly
    -0.09
    ester
    -0.09
     familiar
    -0.08
    insula
    -0.08
    enburg
    -0.08
     sane
    -0.08
     goodies
    -0.08
    POSITIVE LOGITS
     term
    0.14
     phenomenon
    0.14
     refers
    0.13
     whereby
    0.13
     derog
    0.12
     wherein
    0.12
     describes
    0.12
     phrase
    0.11
     compliment
    0.11
     coined
    0.11
    Activations Density 0.159%

    No Known Activations