© 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. 113391
    Prev
    Next
    INDEX
    Explanations

    phrase following parenthesis

    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
    --↵
    -0.13
    jis
    -0.11
     --↵
    -0.10
     |↵
    -0.10
     (↵
    -0.10
     PIE
    -0.10
    ined
    -0.10
     __________________↵↵
    -0.10
    :`
    -0.10
    ı
    -0.10
    POSITIVE LOGITS
     ”
    0.11
     Rabbit
    0.11
     wid
    0.10
    823
    0.09
     cla
    0.09
     Globe
    0.09
    [âĢ¦
    0.09
    562
    0.09
     nag
    0.09
    \t
    0.08
    Activations Density 0.065%

    No Known Activations