© 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. 113141
    Prev
    Next
    INDEX
    Explanations

    name or item description

    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
     hopefully
    -0.13
    quil
    -0.12
     pupper
    -0.12
    hopefully
    -0.12
     conveniently
    -0.12
    asons
    -0.12
    Plus
    -0.12
     knowingly
    -0.11
    hope
    -0.11
     Pul
    -0.11
    POSITIVE LOGITS
     preferably
    0.10
     ideally
    0.10
     Liber
    0.09
     Bain
    0.08
     especially
    0.08
     moderately
    0.08
     Don
    0.08
     chances
    0.08
     Avoid
    0.08
     rather
    0.08
    Activations Density 0.124%

    No Known Activations