© 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. 112901
    Prev
    Next
    INDEX
    Explanations

    pre-

    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
    omatic
    -0.10
    endor
    -0.08
     chatt
    -0.08
     erotica
    -0.07
     downstream
    -0.07
     laure
    -0.07
    omic
    -0.07
     hugely
    -0.07
     botanical
    -0.07
     infl
    -0.07
    POSITIVE LOGITS
    pped
    0.14
     prep
    0.14
     preparations
    0.12
    ceeded
    0.12
    /pre
    0.11
    /pro
    0.11
     Prep
    0.11
    ço
    0.11
     brit
    0.11
    prep
    0.10
    Activations Density 0.009%

    No Known Activations