© 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. 3904
    Prev
    Next
    INDEX
    Explanations

    the first / one / main / biggest

    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
     chances
    -0.10
     Worst
    -0.09
    amat
    -0.09
     Examples
    -0.08
    examples
    -0.08
    acf
    -0.08
    heimer
    -0.08
     Worse
    -0.08
    appro
    -0.08
     mediocre
    -0.08
    POSITIVE LOGITS
     noticeable
    0.16
     notable
    0.14
     significant
    0.14
     noteworthy
    0.14
     surprising
    0.14
     major
    0.14
     striking
    0.14
     startling
    0.13
     interesting
    0.13
     thing
    0.13
    Activations Density 0.141%

    No Known Activations