© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116101
    Prev
    Next
    INDEX
    Explanations

    time continuation

    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
     [âĢ¦]↵↵
    -0.19
     [âĢ¦
    -0.13
     (...)
    -0.09
     [...]
    -0.09
     [âĢ¦]
    -0.09
    <|fim_suffix|>
    -0.09
     [...]↵↵
    -0.08
    [âĢ¦
    -0.07
    [âĢ¦]
    -0.07
    swick
    -0.07
    POSITIVE LOGITS
    zer
    0.08
    -</
    0.08
    sitemap
    0.07
    abo
    0.07
     :</
    0.07
    _frontend
    0.07
    ÃŁer
    0.07
     aforementioned
    0.07
    zion
    0.07
    abbo
    0.07
    Activations Density 0.210%

    No Known Activations