© 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. 89399
    Prev
    Next
    INDEX
    Explanations

    and finalize

    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
    ONA
    -0.12
     succesfully
    -0.11
     successfully
    -0.11
     Gat
    -0.11
     occasionally
    -0.10
     Took
    -0.10
     hesitate
    -0.10
     verst
    -0.10
    asan
    -0.10
     Maintain
    -0.10
    POSITIVE LOGITS
     maybe
    0.17
     then
    0.17
     we
    0.16
     hopefully
    0.15
     perhaps
    0.14
    Then
    0.13
     you
    0.13
     THEN
    0.13
    Maybe
    0.13
    maybe
    0.13
    Activations Density 0.045%

    No Known Activations