© 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. 31301
    Prev
    Next
    INDEX
    Explanations

    description of behavior, coupling, or process

    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
    arda
    -0.11
     Butler
    -0.10
     Ris
    -0.09
     Rise
    -0.09
    ifen
    -0.08
    aida
    -0.08
     Tok
    -0.08
    oping
    -0.08
    /List
    -0.08
     Dexter
    -0.08
    POSITIVE LOGITS
     description
    0.17
     descriptions
    0.15
     portrayed
    0.15
     described
    0.15
    -themed
    0.14
     showcased
    0.14
     represented
    0.14
     depicted
    0.14
     reported
    0.14
    -focused
    0.13
    Activations Density 1.849%

    No Known Activations