© 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. 31308
    Prev
    Next
    INDEX
    Explanations

    for reasons explained

    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
     pob
    -0.09
     unfinished
    -0.09
    aber
    -0.09
     Gra
    -0.08
    arda
    -0.08
     tasted
    -0.08
    sti
    -0.08
     frequ
    -0.08
    eer
    -0.08
    alls
    -0.08
    POSITIVE LOGITS
     inexp
    0.15
    explained
    0.12
     unclear
    0.11
     debated
    0.11
    idle
    0.10
    OUN
    0.10
     strictly
    0.10
     explained
    0.10
    -disc
    0.10
    584
    0.10
    Activations Density 0.026%

    No Known Activations