© 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. 30369
    Prev
    Next
    INDEX
    Explanations

    message me for details

    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
     Bookmark
    -0.12
    pred
    -0.12
    /Dk
    -0.11
     Meng
    -0.11
    nor
    -0.11
     repetition
    -0.11
     nor
    -0.11
    qn
    -0.11
     (?)
    -0.10
     interv
    -0.10
    POSITIVE LOGITS
     detailing
    0.11
     letting
    0.11
     details
    0.10
     if
    0.09
     interested
    0.09
     ASAP
    0.09
     outlining
    0.08
     impl
    0.08
     Sutton
    0.08
    Interested
    0.08
    Activations Density 0.033%

    No Known Activations