© 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. 27763
    Prev
    Next
    INDEX
    Explanations

    account features

    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
     Pear
    -0.07
     frank
    -0.07
     rak
    -0.06
     meticulously
    -0.06
    agn
    -0.06
     FileManager
    -0.06
    209
    -0.06
     Fulton
    -0.06
     proph
    -0.06
     Bowman
    -0.06
    POSITIVE LOGITS
     possibility
    0.12
     "\(
    0.12
     ort
    0.11
     POSSIBILITY
    0.11
     infos
    0.11
     slug
    0.11
     Variety
    0.11
    IDEO
    0.11
     restr
    0.11
    (avg
    0.10
    Activations Density 0.018%

    No Known Activations