© 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. 89363
    Prev
    Next
    INDEX
    Explanations

    saying, getting, outside, leaves, fetch, measurement

    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
     accidental
    -0.11
     unintention
    -0.10
    722
    -0.10
     unpl
    -0.10
     unintended
    -0.09
    hid
    -0.09
     Mun
    -0.09
     hypoth
    -0.09
    ossier
    -0.09
     bree
    -0.09
    POSITIVE LOGITS
     evidently
    0.15
     apparently
    0.13
    æŃ£åľ¨
    0.13
     surrounded
    0.12
     obviously
    0.11
     seemingly
    0.11
     visibly
    0.11
     Apparently
    0.10
     underway
    0.09
    /lg
    0.09
    Activations Density 0.058%

    No Known Activations