© 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. 88007
    Prev
    Next
    INDEX
    Explanations

    client-initiated bootstrap

    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
     fucks
    -0.11
     beet
    -0.08
    arga
    -0.08
     succinct
    -0.08
     rounded
    -0.08
     langu
    -0.08
    /lg
    -0.08
     rapes
    -0.08
     exposures
    -0.08
     chambers
    -0.08
    POSITIVE LOGITS
     embarrassing
    0.13
     embarrassed
    0.11
     hic
    0.11
     celebrity
    0.11
     prom
    0.11
     stalk
    0.11
     bald
    0.11
     compliment
    0.11
     prank
    0.11
     crying
    0.11
    Activations Density 0.005%

    No Known Activations