© 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. 47448
    Prev
    Next
    INDEX
    Explanations

    famous person described by titles

    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
    whatever
    -0.11
    —"
    -0.10
    idot
    -0.10
     ATP
    -0.10
     whatever
    -0.10
     WHATSOEVER
    -0.10
     Pharm
    -0.10
    anko
    -0.10
    657
    -0.10
    ennen
    -0.09
    POSITIVE LOGITS
     fellow
    0.19
     famed
    0.19
     renowned
    0.17
     infamous
    0.15
     famous
    0.14
     notorious
    0.14
     the
    0.13
     controversial
    0.12
     legendary
    0.12
     prominent
    0.12
    Activations Density 1.448%

    No Known Activations