© 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. 116782
    Prev
    Next
    INDEX
    Explanations

    technical contexts or lists

    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
     somewhat
    -0.13
    —which
    -0.12
     completely
    -0.11
     somebody
    -0.11
    (which
    -0.11
     underneath
    -0.10
     endeavour
    -0.10
     Needless
    -0.10
    ä¹ĭ
    -0.10
     specifically
    -0.10
    POSITIVE LOGITS
    éľĢ
    0.13
     diverse
    0.12
     sans
    0.12
    没
    0.11
    others
    0.11
     risking
    0.10
     &
    0.10
     info
    0.10
     èĭ¥
    0.10
     FAQs
    0.10
    Activations Density 0.431%

    No Known Activations