© 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. 114732
    Prev
    Next
    INDEX
    Explanations

    because cause and effect

    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
    dee
    -0.11
     thrift
    -0.11
     ach
    -0.10
     nas
    -0.10
     Lamp
    -0.10
    *&
    -0.10
    bach
    -0.10
     suffers
    -0.10
    abal
    -0.10
     umb
    -0.10
    POSITIVE LOGITS
     presumably
    0.12
     suddenly
    0.10
     Unable
    0.09
    RITE
    0.09
     distraction
    0.09
     drowned
    0.09
     Mime
    0.09
     Hammond
    0.09
    si
    0.08
    JR
    0.08
    Activations Density 0.270%

    No Known Activations