© 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. 31849
    Prev
    Next
    INDEX
    Explanations

    names followed by years

    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
    asia
    -0.12
    /proto
    -0.09
     Ashton
    -0.09
    amate
    -0.09
    ffa
    -0.09
    notation
    -0.09
    /constants
    -0.09
     Toro
    -0.08
    IID
    -0.08
     Levine
    -0.08
    POSITIVE LOGITS
    DDS
    0.21
    STS
    0.20
    ARDS
    0.20
     Sachs
    0.20
    RICS
    0.19
     Adams
    0.19
     Hicks
    0.18
    PTS
    0.18
     Nichols
    0.18
    (nums
    0.18
    Activations Density 0.683%

    No Known Activations