© 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. 48720
    Prev
    Next
    INDEX
    Explanations

    had their

    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
    ider
    -0.10
    ipp
    -0.10
     Pis
    -0.09
    å¤ĩ
    -0.09
    usch
    -0.09
    ologies
    -0.09
     ero
    -0.09
     Fus
    -0.09
    ischer
    -0.09
    iddy
    -0.09
    POSITIVE LOGITS
     seus
    0.12
     holes
    0.11
     seu
    0.11
    ngo
    0.11
     portions
    0.10
     sua
    0.10
     their
    0.10
     its
    0.10
    aho
    0.10
     seams
    0.10
    Activations Density 0.409%

    No Known Activations