© 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. 90331
    Prev
    Next
    INDEX
    Explanations

    viewing messages

    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
     unexpectedly
    -0.10
    DIC
    -0.09
     unexpected
    -0.09
     Vega
    -0.08
     increasingly
    -0.08
    Æ¡n
    -0.08
    irit
    -0.08
     Emin
    -0.08
     Unexpected
    -0.08
     Ridley
    -0.08
    POSITIVE LOGITS
     today
    0.16
     TODAY
    0.14
    !:
    0.12
    !↵↵↵↵↵↵
    0.12
     tonight
    0.12
     tomorrow
    0.12
     Today
    0.12
    today
    0.11
     aujourd
    0.11
    !/
    0.11
    Activations Density 0.053%

    No Known Activations