© 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. 17114
    Prev
    Next
    INDEX
    Explanations

    bodily, Bodleian, Bodnar, Bodhi, BODs, Bodipy

    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
    ing
    -0.10
     honor
    -0.10
     trad
    -0.09
    hoot
    -0.08
    ogue
    -0.08
    hof
    -0.08
     Maur
    -0.08
    lect
    -0.08
    lining
    -0.08
    ongs
    -0.08
    POSITIVE LOGITS
    acious
    0.12
    ysize
    0.10
    iless
    0.10
    acia
    0.10
    ys
    0.10
    asso
    0.10
    rum
    0.10
    iful
    0.09
    anno
    0.09
    avirus
    0.09
    Activations Density 0.003%

    No Known Activations