© 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. 6314
    Prev
    Next
    INDEX
    Explanations

    distance to

    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
     widow
    -0.11
    ÑĤо
    -0.09
     bully
    -0.09
    351
    -0.09
     su
    -0.09
    enda
    -0.09
    dec
    -0.09
    .rs
    -0.09
    bla
    -0.09
    /front
    -0.08
    POSITIVE LOGITS
     choice
    0.15
     to
    0.14
     way
    0.14
     place
    0.12
    choice
    0.12
     anz
    0.12
     for
    0.11
     Choice
    0.10
     basis
    0.10
    Choice
    0.10
    Activations Density 0.088%

    No Known Activations