© 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. 14510
    Prev
    Next
    INDEX
    Explanations

    dates, metadata, and questions

    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
     causa
    -0.09
     Wolff
    -0.09
    <article
    -0.09
     streak
    -0.09
     nost
    -0.09
     woo
    -0.09
    EMS
    -0.08
     moderated
    -0.08
     sadd
    -0.08
    ttp
    -0.08
    POSITIVE LOGITS
    enda
    0.11
     underestimate
    0.11
     Smash
    0.11
     unf
    0.10
    MEA
    0.10
     Prepared
    0.10
    -confirm
    0.09
     Trophy
    0.09
     nails
    0.09
     impatient
    0.09
    Activations Density 0.002%

    No Known Activations