© 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. 16204
    Prev
    Next
    INDEX
    Explanations

    I'm / we are

    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
     apparently
    -0.14
     reportedly
    -0.13
     Apparently
    -0.13
     admittedly
    -0.13
     evidently
    -0.12
     presumably
    -0.12
     remember
    -0.11
    Apparently
    -0.11
     IMO
    -0.11
     remembered
    -0.11
    POSITIVE LOGITS
     hardly
    0.11
    .bi
    0.10
    ?"↵↵↵↵
    0.10
    oly
    0.09
     always
    0.09
     Hook
    0.09
     glyc
    0.09
    pai
    0.09
     subscript
    0.09
    obi
    0.09
    Activations Density 0.224%

    No Known Activations