© 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. 114916
    Prev
    Next
    INDEX
    Explanations

    of course

    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
    asse
    -0.11
    820
    -0.11
    iant
    -0.09
    istant
    -0.08
    OK
    -0.08
     apl
    -0.08
    antage
    -0.08
     Holden
    -0.08
     prospect
    -0.08
    adel
    -0.08
    POSITIVE LOGITS
     course
    0.24
     COUR
    0.17
     Course
    0.15
    course
    0.15
    -course
    0.14
     necessity
    0.14
     cour
    0.12
     whom
    0.12
     cours
    0.12
     which
    0.12
    Activations Density 0.072%

    No Known Activations