© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16367
    Prev
    Next
    INDEX
    Explanations

    XML tag 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
     aforementioned
    -0.06
    ernen
    -0.06
     pretty
    -0.06
    àµį
    -0.06
     ...↵
    -0.06
    pretty
    -0.05
     eles
    -0.05
    onio
    -0.05
     fos
    -0.05
    heim
    -0.05
    POSITIVE LOGITS
    Sdk
    0.12
    ilen
    0.12
    uisse
    0.11
    ainter
    0.11
    estone
    0.11
    uki
    0.10
    /domain
    0.10
    Badge
    0.10
    {})
    0.10
    oru
    0.10
    Activations Density 0.600%

    No Known Activations