© 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. 6513
    Prev
    Next
    INDEX
    Explanations

    mentioning or describing

    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
    nergy
    -0.08
    åľ¨
    -0.08
    leaf
    -0.07
     HS
    -0.07
    ng
    -0.07
     Shell
    -0.07
     quali
    -0.07
    lect
    -0.07
    cek
    -0.07
    urred
    -0.07
    POSITIVE LOGITS
     mention
    0.14
     mentions
    0.14
    ernes
    0.13
     mentioned
    0.13
     appears
    0.12
     heiÃŁ
    0.12
     stated
    0.12
     refers
    0.12
     describes
    0.12
     Appears
    0.12
    Activations Density 0.721%

    No Known Activations