© 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. 16340
    Prev
    Next
    INDEX
    Explanations

    dispose, look

    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
     Cro
    -0.10
    GRA
    -0.10
    lid
    -0.10
    ienes
    -0.10
     Curriculum
    -0.10
    ["$
    -0.10
    nine
    -0.10
     paced
    -0.10
     GDK
    -0.10
    Coder
    -0.10
    POSITIVE LOGITS
     the
    0.11
     fot
    0.08
     some
    0.07
     their
    0.07
    atar
    0.07
     these
    0.07
    /bind
    0.07
     dao
    0.07
     any
    0.07
     those
    0.07
    Activations Density 0.530%

    No Known Activations