© 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. 15397
    Prev
    Next
    INDEX
    Explanations

    take for example

    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
    ahn
    -0.09
    laps
    -0.09
     rond
    -0.09
    NCY
    -0.09
    ilk
    -0.09
    getAs
    -0.09
    abis
    -0.08
    Bean
    -0.08
    *****č↵
    -0.08
    udd
    -0.08
    POSITIVE LOGITS
     example
    0.17
     Example
    0.15
    ä¾ĭå¦Ĥ
    0.14
    Example
    0.14
    example
    0.12
     case
    0.12
     instance
    0.12
    case
    0.12
     exemple
    0.12
     EXAMPLE
    0.11
    Activations Density 0.075%

    No Known Activations