© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27555
    Prev
    Next
    INDEX
    Explanations

    send or forward with recipient

    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
     disse
    -0.11
     imperson
    -0.10
    ello
    -0.10
     dissemination
    -0.09
     Wass
    -0.09
     purposely
    -0.09
     transmitting
    -0.09
    ior
    -0.09
     handmade
    -0.09
     unnecessarily
    -0.09
    POSITIVE LOGITS
     along
    0.11
    along
    0.11
     watering
    0.10
    Dims
    0.10
     vog
    0.10
    /category
    0.10
    Votes
    0.10
     regrets
    0.10
     ¥
    0.10
     pint
    0.09
    Activations Density 0.053%

    No Known Activations