© 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. 15359
    Prev
    Next
    INDEX
    Explanations

    the rest of the

    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
     widest
    -0.11
    anus
    -0.09
    iel
    -0.09
     slightest
    -0.08
     mere
    -0.08
     Friendship
    -0.08
     Caption
    -0.08
     weakest
    -0.08
     beginnings
    -0.08
    TK
    -0.08
    POSITIVE LOGITS
     ench
    0.12
     stuff
    0.12
     iceberg
    0.11
     trilogy
    0.11
     journey
    0.11
     ilk
    0.10
     story
    0.10
     ingredients
    0.10
    world
    0.10
     Informationen
    0.10
    Activations Density 0.035%

    No Known Activations