© 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. 92053
    Prev
    Next
    INDEX
    Explanations

    future hopes and possibilities

    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
    idak
    -0.11
     Emb
    -0.10
     Crosby
    -0.10
    adro
    -0.09
    hdl
    -0.09
     Um
    -0.09
     struggled
    -0.09
    urette
    -0.09
     please
    -0.09
     Zimmer
    -0.09
    POSITIVE LOGITS
     tomorrow
    0.20
     hopefully
    0.18
     Hopefully
    0.17
     Tomorrow
    0.17
    Tomorrow
    0.16
    Hopefully
    0.14
     someday
    0.13
     hmm
    0.13
     exits
    0.13
     chuck
    0.13
    Activations Density 0.018%

    No Known Activations