© 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. 28079
    Prev
    Next
    INDEX
    Explanations

    automatic and autonomic processes

    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
     unexpectedly
    -0.11
     trajectories
    -0.09
    unden
    -0.09
     unprecedented
    -0.09
    oki
    -0.09
     hes
    -0.09
     unexpected
    -0.09
     Emoji
    -0.09
     ASN
    -0.09
    Nullable
    -0.09
    POSITIVE LOGITS
     automatic
    0.34
     Automatic
    0.27
     automatically
    0.27
    automatic
    0.27
     unconscious
    0.26
     reflex
    0.26
    Automatic
    0.26
     subconscious
    0.25
     automat
    0.25
    -automatic
    0.23
    Activations Density 0.148%

    No Known Activations