© 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. 50092
    Prev
    Next
    INDEX
    Explanations

    -ing words: building, looking, taking, being, repairing, finishing, splitting

    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
    .asp
    -0.10
    ussen
    -0.09
    YPE
    -0.08
     Guerrero
    -0.08
    lot
    -0.08
    ibel
    -0.08
    wald
    -0.08
     Nord
    -0.08
    adesh
    -0.08
     Fuj
    -0.08
    POSITIVE LOGITS
     being
    0.15
    being
    0.14
     Being
    0.12
    Being
    0.12
     having
    0.11
     needing
    0.11
     Having
    0.10
    mil
    0.10
    having
    0.10
     wanting
    0.10
    Activations Density 0.142%

    No Known Activations