© 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. 116998
    Prev
    Next
    INDEX
    Explanations

    people in groups

    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
    baugh
    -0.09
     retract
    -0.09
     Diff
    -0.09
     ends
    -0.09
    tones
    -0.08
     Morg
    -0.08
     concent
    -0.08
    å¼ı
    -0.08
     Prest
    -0.08
    etus
    -0.08
    POSITIVE LOGITS
    -turned
    0.18
     who
    0.11
    /engine
    0.11
    /student
    0.11
     unrest
    0.10
     gar
    0.10
     handbook
    0.10
    /pol
    0.10
    innen
    0.10
     unfamiliar
    0.09
    Activations Density 0.220%

    No Known Activations