© 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. 6064
    Prev
    Next
    INDEX
    Explanations

    text in parentheses

    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
    auth
    -0.10
     Dustin
    -0.08
    conj
    -0.08
     Â
    -0.08
    quia
    -0.08
     stil
    -0.07
    unt
    -0.07
     Covent
    -0.07
    atl
    -0.07
    jo
    -0.07
    POSITIVE LOGITS
    (s
    0.18
    们
    0.13
    [s
    0.13
    tries
    0.12
    -ing
    0.11
    ing
    0.11
    -ie
    0.10
     dug
    0.10
    à¹Į
    0.10
    -ed
    0.10
    Activations Density 0.026%

    No Known Activations