© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    keep or keeping

    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
     keeping
    -0.11
    661
    -0.11
    ideo
    -0.10
    ulle
    -0.10
     soon
    -0.10
    ez
    -0.09
    uel
    -0.09
    unts
    -0.09
     whilst
    -0.09
    kept
    -0.09
    POSITIVE LOGITS
     track
    0.19
     tabs
    0.17
    dims
    0.13
    akes
    0.12
     Tabs
    0.12
     abre
    0.12
    ake
    0.12
     everything
    0.11
     pace
    0.11
     Track
    0.11
    Activations Density 0.028%

    No Known Activations