© 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. 17643
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    yal
    -0.11
    /root
    -0.10
     intending
    -0.10
    /cal
    -0.09
     likely
    -0.09
    usual
    -0.09
    vez
    -0.09
     Kata
    -0.09
    otch
    -0.09
    Translations
    -0.09
    POSITIVE LOGITS
     well
    0.21
     wells
    0.14
     evidenced
    0.14
    well
    0.13
     opposed
    0.13
     Well
    0.12
     demonstrated
    0.12
     seen
    0.12
     WELL
    0.12
     outlined
    0.12
    Activations Density 0.297%

    No Known Activations