© 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. 28664
    Prev
    Next
    INDEX
    Explanations

    number or word sequences

    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
    —↵↵
    -0.12
    âĢķ
    -0.12
     Gotham
    -0.12
     dirig
    -0.12
    —or
    -0.12
     fifteen
    -0.12
     fifty
    -0.12
     twenty
    -0.11
    |M
    -0.11
     nineteen
    -0.11
    POSITIVE LOGITS
     (~
    0.17
     VERY
    0.15
     approx
    0.13
     ppl
    0.12
     dept
    0.11
     Univ
    0.11
     very
    0.11
     guy
    0.11
     thru
    0.11
     Dept
    0.10
    Activations Density 1.303%

    No Known Activations