© 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. 31633
    Prev
    Next
    INDEX
    Explanations

    location names

    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
    umper
    -0.13
     Asheville
    -0.12
     Dylan
    -0.12
    asi
    -0.11
    compat
    -0.11
     redeem
    -0.11
    arel
    -0.11
    .setAuto
    -0.11
     Episodes
    -0.11
    NORMAL
    -0.11
    POSITIVE LOGITS
     populous
    0.08
     manually
    0.08
     populated
    0.07
     Gregg
    0.07
     pop
    0.07
     precis
    0.06
     strategically
    0.06
     ("
    0.06
    fax
    0.06
     Greater
    0.06
    Activations Density 0.029%

    No Known Activations