© 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. 30904
    Prev
    Next
    INDEX
    Explanations

    first encounters or discoveries

    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
     Hoff
    -0.11
     seldom
    -0.10
    eldom
    -0.09
     conveniently
    -0.09
     saat
    -0.08
    aunch
    -0.08
     enn
    -0.08
     inconvenient
    -0.08
     campaigning
    -0.08
     rarely
    -0.08
    POSITIVE LOGITS
     inkl
    0.15
     ever
    0.15
    -ever
    0.15
     consciously
    0.15
     knowingly
    0.15
     explicit
    0.13
     truly
    0.13
     aware
    0.13
     EVER
    0.12
     realization
    0.12
    Activations Density 0.084%

    No Known Activations