© 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. 48361
    Prev
    Next
    INDEX
    Explanations

    not happen

    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
     misunder
    -0.11
     neither
    -0.10
    aec
    -0.10
     Qi
    -0.10
    zm
    -0.10
    _handles
    -0.10
     Gä
    -0.10
    vr
    -0.10
    vla
    -0.09
     never
    -0.09
    POSITIVE LOGITS
     mattered
    0.15
     comport
    0.13
     matter
    0.13
     detr
    0.12
     align
    0.12
     match
    0.11
     deter
    0.11
     affect
    0.11
     conform
    0.11
     correspond
    0.10
    Activations Density 0.124%

    No Known Activations