© 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. 7765
    Prev
    Next
    INDEX
    Explanations

    Essays, narratives, and sketches

    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
     Shine
    -0.10
     Hurt
    -0.09
     unthinkable
    -0.09
     dysfunctional
    -0.08
     unstoppable
    -0.08
     sensing
    -0.08
    .mapping
    -0.08
     messy
    -0.08
     repeat
    -0.08
     Circus
    -0.08
    POSITIVE LOGITS
     Sketch
    0.16
    Sketch
    0.12
     reprint
    0.12
     Outline
    0.12
     Upon
    0.11
     Illustr
    0.11
    Entered
    0.11
     sketches
    0.11
     upon
    0.11
     treat
    0.10
    Activations Density 0.828%

    No Known Activations