© 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. 18250
    Prev
    Next
    INDEX
    Explanations

    John followed by certain names

    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
    fts
    -0.11
    undi
    -0.11
    âķIJ
    -0.09
    integr
    -0.09
    cio
    -0.09
    itious
    -0.09
    onds
    -0.09
     bour
    -0.09
    velt
    -0.09
    elu
    -0.09
    POSITIVE LOGITS
    athan
    0.26
    nie
    0.23
    athon
    0.18
    ny
    0.14
    stone
    0.13
    stown
    0.13
    ston
    0.12
    atan
    0.12
     Doe
    0.11
     Cena
    0.11
    Activations Density 0.096%

    No Known Activations