© 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. 47983
    Prev
    Next
    INDEX
    Explanations

    more specifically

    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
    ¿
    -0.09
    772
    -0.08
     tact
    -0.08
    urf
    -0.08
     Loren
    -0.08
    coord
    -0.08
     Quarter
    -0.07
     adrenaline
    -0.07
     Wit
    -0.07
     ensuring
    -0.07
    POSITIVE LOGITS
    );↵↵↵↵↵
    0.11
     duplicated
    0.11
    agy
    0.10
    ialized
    0.10
     Dew
    0.10
     schön
    0.10
     additionally
    0.10
     ag
    0.10
     STOCK
    0.10
     Floors
    0.10
    Activations Density 0.109%

    No Known Activations