© 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. 47513
    Prev
    Next
    INDEX
    Explanations

    energy source modifier

    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
    een
    -0.08
    ments
    -0.07
     airborne
    -0.07
     breath
    -0.07
     Lunch
    -0.07
     Lod
    -0.06
     IM
    -0.06
     sniff
    -0.06
    ment
    -0.06
     mailing
    -0.06
    POSITIVE LOGITS
     contrace
    0.13
     sex
    0.11
     sill
    0.11
    bac
    0.11
    quot
    0.11
     +/-
    0.11
     Leban
    0.11
     favors
    0.11
     ved
    0.11
    /constants
    0.11
    Activations Density 0.005%

    No Known Activations