© 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. 47846
    Prev
    Next
    INDEX
    Explanations

    point from, ace on, order from

    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
     throughout
    -0.13
     systematically
    -0.13
     consistently
    -0.13
     extensively
    -0.12
     increasingly
    -0.12
     relentlessly
    -0.12
     diligently
    -0.12
     everywhere
    -0.11
     tirelessly
    -0.11
     continuously
    -0.11
    POSITIVE LOGITS
     followed
    0.13
    (s
    0.13
     smack
    0.10
     pair
    0.09
     right
    0.09
    [s
    0.08
     lonely
    0.08
    vide
    0.08
     near
    0.08
     landed
    0.08
    Activations Density 0.140%

    No Known Activations