© 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. 7535
    Prev
    Next
    INDEX
    Explanations

    Chuck names

    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
    yte
    -0.10
     routine
    -0.09
     Chatt
    -0.09
     rough
    -0.09
     Grave
    -0.08
    imum
    -0.08
    er
    -0.08
     evid
    -0.08
     volta
    -0.08
    oud
    -0.08
    POSITIVE LOGITS
    ie
    0.11
    les
    0.11
    ups
    0.10
    aby
    0.10
    yna
    0.10
    efe
    0.10
    levision
    0.10
    uito
    0.10
    abbage
    0.09
     (!((
    0.09
    Activations Density 0.008%

    No Known Activations