© 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. 16152
    Prev
    Next
    INDEX
    Explanations

    ANY KIND OR WARRANTY

    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
    udev
    -0.11
    usch
    -0.11
    iamo
    -0.11
    ergy
    -0.11
    /npm
    -0.10
    ny
    -0.10
    olare
    -0.10
    eus
    -0.10
     leveled
    -0.10
    anime
    -0.10
    POSITIVE LOGITS
     virtue
    0.08
     medicine
    0.08
     basics
    0.08
    /re
    0.08
    cka
    0.08
    459
    0.07
     ic
    0.07
     Kale
    0.07
    hin
    0.07
     scientifically
    0.07
    Activations Density 0.003%

    No Known Activations