© 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. 88386
    Prev
    Next
    INDEX
    Explanations

    project director, survived, murder, announcing

    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
    umper
    -0.11
     truly
    -0.11
    oser
    -0.10
    oucher
    -0.10
     Truly
    -0.10
    afi
    -0.09
    otime
    -0.09
     ugl
    -0.09
     Lester
    -0.09
    bern
    -0.09
    POSITIVE LOGITS
     freaking
    0.17
     fucking
    0.13
     potentially
    0.13
     nearly
    0.12
     literal
    0.12
     giant
    0.12
     thousands
    0.11
     murder
    0.11
     fr
    0.11
     hundreds
    0.11
    Activations Density 0.363%

    No Known Activations