© 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. 33764
    Prev
    Next
    INDEX
    Explanations

    company or product 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
     Pitch
    -0.08
     Photographer
    -0.08
     Mayor
    -0.07
     vess
    -0.07
     Zar
    -0.07
     Lawyer
    -0.07
     ais
    -0.07
     Routine
    -0.07
     arist
    -0.07
     Stake
    -0.07
    POSITIVE LOGITS
     Studios
    0.15
     Enterprises
    0.15
     Technologies
    0.14
     Networks
    0.14
     magazine
    0.14
     Productions
    0.13
     Publishing
    0.13
     Communications
    0.13
     Natur
    0.13
     Group
    0.13
    Activations Density 0.607%

    No Known Activations