© 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. 32255
    Prev
    Next
    INDEX
    Explanations

    but but but

    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
     occasionally
    -0.12
     zwar
    -0.11
    isser
    -0.10
     slightly
    -0.10
     reluctantly
    -0.09
    _mB
    -0.09
     doubly
    -0.09
     occasional
    -0.09
     Patterson
    -0.09
     Gateway
    -0.09
    POSITIVE LOGITS
     mostly
    0.38
     overall
    0.37
     mainly
    0.35
     Mostly
    0.35
     predominantly
    0.34
     primarily
    0.34
    mostly
    0.30
     chiefly
    0.29
     Overall
    0.29
     principally
    0.28
    Activations Density 0.310%

    No Known Activations