© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27118
    Prev
    Next
    INDEX
    Explanations

    .app followed by .Activity or .Dialog

    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
    s
    -0.10
     bfd
    -0.08
    nier
    -0.08
    achel
    -0.08
    illos
    -0.08
     tipping
    -0.08
    dana
    -0.08
    gn
    -0.08
    rosse
    -0.08
    !↵↵↵↵↵↵
    -0.08
    POSITIVE LOGITS
     rede
    0.11
     tack
    0.11
     fool
    0.10
     Domino
    0.09
     patron
    0.09
    trad
    0.09
    -that
    0.09
     dom
    0.09
     fol
    0.09
    arel
    0.09
    Activations Density 0.011%

    No Known Activations