© 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. 113630
    Prev
    Next
    INDEX
    Explanations

    of a

    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
     Affordable
    -0.09
    linky
    -0.09
    -SA
    -0.09
     Boone
    -0.09
    oop
    -0.09
     squat
    -0.09
     dow
    -0.09
    460
    -0.09
     steadfast
    -0.09
     highly
    -0.08
    POSITIVE LOGITS
     chalk
    0.09
     Nem
    0.09
    pla
    0.08
     Tome
    0.08
     Castro
    0.08
    .qual
    0.07
     stalking
    0.07
    bero
    0.07
    bread
    0.07
    ssql
    0.07
    Activations Density 0.001%

    No Known Activations