© 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. 26696
    Prev
    Next
    INDEX
    Explanations

    primitive or basic

    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
     voluntarily
    -0.11
     mild
    -0.10
    midd
    -0.09
     Moderate
    -0.09
     grac
    -0.09
     Balt
    -0.09
     tid
    -0.09
     Friendly
    -0.09
    Dry
    -0.09
     upbeat
    -0.08
    POSITIVE LOGITS
     primitive
    0.36
     primal
    0.31
     raw
    0.27
     Primitive
    0.27
     instinct
    0.26
    primitive
    0.26
     instincts
    0.25
     primitives
    0.24
    Primitive
    0.24
     visceral
    0.20
    Activations Density 0.142%

    No Known Activations