© 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. 33231
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
     whistle
    -0.11
     Bent
    -0.10
    دÙĩ
    -0.10
    hus
    -0.10
    (optional
    -0.10
    181
    -0.09
    aza
    -0.09
     committing
    -0.09
    leen
    -0.09
    otta
    -0.09
    POSITIVE LOGITS
     interrog
    0.09
     wakes
    0.09
    ething
    0.09
     abroad
    0.09
     proverb
    0.09
     dak
    0.09
     vehement
    0.09
     trusts
    0.08
    /devices
    0.08
     (:
    0.08
    Activations Density 0.008%

    No Known Activations