© 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. 32093
    Prev
    Next
    INDEX
    Explanations

    locations and entities

    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
     Cox
    -0.11
     unm
    -0.09
     McCart
    -0.09
     reim
    -0.09
    è°
    -0.09
    packed
    -0.08
     Cunningham
    -0.08
     Swedish
    -0.08
     consensus
    -0.08
    ()]
    -0.08
    POSITIVE LOGITS
     apologized
    0.09
    oes
    0.09
     Zuk
    0.09
     Sek
    0.09
     Chall
    0.09
    resse
    0.09
    depend
    0.09
     issu
    0.09
    enth
    0.09
     risen
    0.09
    Activations Density 0.020%

    No Known Activations