© 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. 32661
    Prev
    Next
    INDEX
    Explanations

    code comments and programming constructs

    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
     Falk
    -0.08
    <|fim_suffix|>
    -0.08
    ô
    -0.08
    lica
    -0.07
     clinically
    -0.07
     [#
    -0.07
     Morr
    -0.07
     cliff
    -0.07
    iene
    -0.07
     rag
    -0.07
    POSITIVE LOGITS
     avi
    0.11
    cum
    0.11
     gratuit
    0.11
    ÑĤÑĥ
    0.10
    cil
    0.10
     interracial
    0.10
    :');↵
    0.09
     desc
    0.09
     Hari
    0.09
    OPLE
    0.09
    Activations Density 0.003%

    No Known Activations