© 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. 47407
    Prev
    Next
    INDEX
    Explanations

    ical judgments

    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
     ostensibly
    -0.13
     oddly
    -0.12
     staffers
    -0.12
     "...
    -0.11
     decidedly
    -0.11
     seemingly
    -0.11
     Sears
    -0.11
     television
    -0.11
     televis
    -0.11
    Odd
    -0.11
    POSITIVE LOGITS
     Covid
    0.14
    ðŁĺ
    0.13
    ðŁ
    0.12
     kindly
    0.12
     ðĿ
    0.12
     âĿ¤
    0.11
     ðŁĺ
    0.11
     coz
    0.11
     WhatsApp
    0.11
     covid
    0.11
    Activations Density 0.101%

    No Known Activations