© 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. 50110
    Prev
    Next
    INDEX
    Explanations

    ratio

    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
    ifo
    -0.13
    lh
    -0.11
    hung
    -0.11
     Total
    -0.11
    Sz
    -0.11
    ilan
    -0.11
    _Total
    -0.10
     Ranked
    -0.10
    otal
    -0.10
    -total
    -0.10
    POSITIVE LOGITS
     ten
    0.23
     TEN
    0.17
     five
    0.17
     three
    0.16
     nine
    0.15
     dozen
    0.15
    ten
    0.15
     two
    0.15
     hundred
    0.14
     four
    0.13
    Activations Density 0.480%

    No Known Activations