© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 112139
    Prev
    Next
    INDEX
    Explanations

    placed inside

    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
     Briggs
    -0.11
     cas
    -0.10
     Walsh
    -0.09
     Compass
    -0.09
    rub
    -0.09
    simulate
    -0.09
     Sidd
    -0.09
     inadvertently
    -0.09
    cas
    -0.08
    oyer
    -0.08
    POSITIVE LOGITS
     capit
    0.11
     comfortably
    0.11
     trusting
    0.11
     willingly
    0.10
     vir
    0.10
     nerv
    0.10
     sanitized
    0.10
    ìĭł
    0.10
    .rev
    0.10
     doc
    0.10
    Activations Density 0.004%

    No Known Activations