© 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. 112850
    Prev
    Next
    INDEX
    Explanations

    Vicente or Victor

    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
    ead
    -0.13
    ecom
    -0.11
     Cond
    -0.10
    e
    -0.10
    Expiration
    -0.09
    evin
    -0.09
     spindle
    -0.09
    ees
    -0.09
    ee
    -0.09
    eenth
    -0.09
    POSITIVE LOGITS
    arious
    0.13
    ente
    0.12
    ENTE
    0.09
    utow
    0.09
    ario
    0.09
     bully
    0.08
     blanks
    0.08
     bio
    0.08
    WISE
    0.08
     Wien
    0.08
    Activations Density 0.001%

    No Known Activations