© 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. 15740
    Prev
    Next
    INDEX
    Explanations

    web services

    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
    arih
    -0.11
     commonplace
    -0.10
     Quar
    -0.09
     Guidelines
    -0.09
     calend
    -0.09
    ippet
    -0.09
    ovic
    -0.09
    enden
    -0.09
     formulation
    -0.09
     Aires
    -0.09
    POSITIVE LOGITS
     without
    0.12
     Without
    0.10
     directly
    0.10
     files
    0.10
    WITHOUT
    0.10
    enders
    0.10
     secretly
    0.09
     USING
    0.09
     silently
    0.09
    agra
    0.09
    Activations Density 0.020%

    No Known Activations