© 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. 27298
    Prev
    Next
    INDEX
    Explanations

    coding structures and keywords

    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
     consenting
    -0.09
     Orch
    -0.07
     dolls
    -0.07
     trembling
    -0.07
     Dispatch
    -0.07
     kod
    -0.07
     Plum
    -0.07
     epith
    -0.07
     sensed
    -0.07
     stockholm
    -0.07
    POSITIVE LOGITS
     exam
    0.13
     concert
    0.13
     homework
    0.13
     tickets
    0.12
     slam
    0.12
     parking
    0.12
     sarc
    0.12
     tomorrow
    0.11
     Theft
    0.11
     ticket
    0.11
    Activations Density 0.195%

    No Known Activations