© 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. 7667
    Prev
    Next
    INDEX
    Explanations

    names and song album titles

    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
     mutant
    -0.10
     rookies
    -0.10
     deer
    -0.10
    pulse
    -0.09
     township
    -0.09
     Ripple
    -0.09
    rollo
    -0.09
     Giles
    -0.09
     Mage
    -0.09
     Pulse
    -0.09
    POSITIVE LOGITS
     Carly
    0.14
     Nickel
    0.14
     Turk
    0.13
     Schneider
    0.12
     Spears
    0.12
     Nev
    0.11
     CPC
    0.10
     Uzbek
    0.10
     Kramer
    0.10
     Gib
    0.10
    Activations Density 0.181%

    No Known Activations