© 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. 116653
    Prev
    Next
    INDEX
    Explanations

    wish for improvements

    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
     Marty
    -0.09
    ült
    -0.09
    ivot
    -0.09
    ât
    -0.09
     coinc
    -0.09
    rys
    -0.08
     Lem
    -0.08
     Downs
    -0.08
    Bạn
    -0.08
     laut
    -0.08
    POSITIVE LOGITS
     ideally
    0.22
     Ideally
    0.19
     wish
    0.18
     Wish
    0.16
     should
    0.16
     wished
    0.16
     would
    0.15
    wish
    0.15
     wishlist
    0.15
     ought
    0.15
    Activations Density 0.850%

    No Known Activations