© 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. 115670
    Prev
    Next
    INDEX
    Explanations

    winding, examination, enzyme, beers

    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
    <|fim_suffix|>
    -0.18
     Survivor
    -0.11
     Britt
    -0.10
     blas
    -0.09
     sl
    -0.09
    <|fim_prefix|>
    -0.09
    ...
    -0.09
     Hull
    -0.09
    ompiler
    -0.08
     asserting
    -0.08
    POSITIVE LOGITS
    illet
    0.09
    erland
    0.09
    odb
    0.08
    RAP
    0.07
    PURE
    0.07
    olson
    0.07
    edm
    0.07
    villa
    0.07
    .www
    0.07
    arra
    0.07
    Activations Density 0.158%

    No Known Activations