© 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. 49188
    Prev
    Next
    INDEX
    Explanations

    Tickets, pills, peptides, books, docs

    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
     pills
    -0.10
     Feinstein
    -0.09
    nesc
    -0.09
     oversh
    -0.08
    _reduction
    -0.08
     Terror
    -0.07
     stepping
    -0.07
     themed
    -0.07
    -themed
    -0.07
    esan
    -0.07
    POSITIVE LOGITS
    antry
    0.12
    dos
    0.11
    asted
    0.11
    .ua
    0.11
    nu
    0.10
    borrow
    0.10
     elo
    0.10
    ares
    0.10
    irk
    0.09
     nu
    0.09
    Activations Density 0.011%

    No Known Activations