© 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. 30427
    Prev
    Next
    INDEX
    Explanations

    license and copyright notices

    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
    ÑĮ
    -0.10
    olate
    -0.10
     prod
    -0.10
     dele
    -0.10
    że
    -0.09
    áŀ¶
    -0.09
    én
    -0.09
    Neutral
    -0.09
    stance
    -0.09
    ette
    -0.09
    POSITIVE LOGITS
     wed
    0.09
     pronto
    0.09
    Ticker
    0.08
     tent
    0.08
    bers
    0.08
     hal
    0.07
     cruc
    0.07
    Stretch
    0.07
    ulation
    0.07
    alic
    0.07
    Activations Density 0.076%

    No Known Activations