© 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. 115553
    Prev
    Next
    INDEX
    Explanations

    know how / understand how

    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
     Kon
    -0.10
    eka
    -0.10
     mature
    -0.10
     Mature
    -0.09
     ancest
    -0.09
    .shtml
    -0.09
     lump
    -0.09
     Lehr
    -0.09
     Supported
    -0.09
     quantitative
    -0.09
    POSITIVE LOGITS
     firsthand
    0.10
    ickle
    0.10
    agu
    0.09
    otec
    0.09
     wr
    0.09
    EA
    0.09
     transformative
    0.08
    ZN
    0.08
     pacing
    0.08
    orno
    0.08
    Activations Density 0.118%

    No Known Activations