© 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. 89863
    Prev
    Next
    INDEX
    Explanations

    directly or explicitly expressed

    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
     TEN
    -0.10
    -relative
    -0.08
     Original
    -0.08
    shortcut
    -0.08
     originals
    -0.08
     realistically
    -0.08
     valid
    -0.08
     impartial
    -0.08
    cac
    -0.08
     mere
    -0.08
    POSITIVE LOGITS
     explicitly
    0.14
     outright
    0.14
     stated
    0.13
     stating
    0.13
    named
    0.11
     confront
    0.11
     SAY
    0.11
     explicit
    0.11
     Explicit
    0.10
     named
    0.10
    Activations Density 0.112%

    No Known Activations