© 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. 27355
    Prev
    Next
    INDEX
    Explanations

    COPY modify reserved license

    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
     afterward
    -0.11
     eventual
    -0.10
     subsequently
    -0.10
    tright
    -0.10
     therein
    -0.10
    âĢ¦)
    -0.10
     [...
    -0.09
     candidacy
    -0.09
    Gatt
    -0.09
     Optionally
    -0.09
    POSITIVE LOGITS
     forbidden
    0.11
     Chinese
    0.10
     mature
    0.09
     teamed
    0.09
     Christmas
    0.09
     deceptive
    0.09
     Compilation
    0.09
     irresist
    0.09
     hilarious
    0.09
     holiday
    0.09
    Activations Density 0.007%

    No Known Activations