© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91661
    Prev
    Next
    INDEX
    Explanations

    you will find

    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
     willingly
    -0.08
     then
    -0.08
     mann
    -0.08
     deserve
    -0.08
    eneg
    -0.08
     possess
    -0.07
    iren
    -0.07
     sens
    -0.07
    await
    -0.07
    kers
    -0.07
    POSITIVE LOGITS
     encounter
    0.24
     encountering
    0.23
     encounters
    0.23
     Encounter
    0.20
     encountered
    0.19
     encount
    0.17
     finds
    0.16
     find
    0.16
     finding
    0.15
     bump
    0.14
    Activations Density 0.080%

    No Known Activations