© 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. 15067
    Prev
    Next
    INDEX
    Explanations

    numerous indicators

    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
     footage
    -0.09
     коÑĤоÑĢÑĭй
    -0.08
     information
    -0.08
     advant
    -0.07
     progress
    -0.07
     one
    -0.07
     Recommended
    -0.07
     variability
    -0.07
     Legislation
    -0.07
     wrongdoing
    -0.07
    POSITIVE LOGITS
     ones
    0.18
     legion
    0.16
    nt
    0.16
     reflections
    0.14
     clues
    0.14
     manifestations
    0.14
     numerous
    0.14
     indicators
    0.13
     reminders
    0.13
     favorites
    0.13
    Activations Density 0.271%

    No Known Activations