© 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. 33454
    Prev
    Next
    INDEX
    Explanations

    gables, stave, hipped, quark, pendent, thorn, disarray, lacing, turrets

    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
    omore
    -0.11
    perience
    -0.10
    antt
    -0.10
    omen
    -0.09
     swe
    -0.09
    rength
    -0.09
    ponsive
    -0.09
     TOUCH
    -0.09
    ollapse
    -0.09
    orthand
    -0.09
    POSITIVE LOGITS
     shining
    0.11
     plastic
    0.10
    ed
    0.10
     hastily
    0.10
     muted
    0.09
     rounded
    0.09
     faded
    0.09
     dank
    0.09
     obe
    0.09
     shiny
    0.09
    Activations Density 0.208%

    No Known Activations