© 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. 49891
    Prev
    Next
    INDEX
    Explanations

    budget cuts

    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
    board
    -0.10
     unw
    -0.10
     greed
    -0.10
    ventions
    -0.09
     Mattis
    -0.09
    Little
    -0.09
    sv
    -0.08
    .jackson
    -0.08
    roads
    -0.08
    EMENT
    -0.08
    POSITIVE LOGITS
    ary
    0.28
    ARY
    0.19
    -friendly
    0.17
    -conscious
    0.17
    ed
    0.16
    arily
    0.15
    ted
    0.14
    eer
    0.14
    conscious
    0.14
    ing
    0.14
    Activations Density 0.044%

    No Known Activations