© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27633
    Prev
    Next
    INDEX
    Explanations

    in a sense

    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
     somehow
    -0.10
     POSSIBILITY
    -0.09
     possibility
    -0.08
     apparently
    -0.08
     seldom
    -0.08
     originally
    -0.08
    anger
    -0.08
     normally
    -0.08
     rarely
    -0.08
     generally
    -0.08
    POSITIVE LOGITS
     resembles
    0.15
     resemble
    0.15
     similar
    0.12
     reminiscent
    0.12
    similar
    0.12
     resembled
    0.12
     simpler
    0.11
     easier
    0.11
     analogous
    0.11
    jom
    0.11
    Activations Density 0.095%

    No Known Activations