© 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. 115435
    Prev
    Next
    INDEX
    Explanations

    mus/muse following or preceding name segments

    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
    thon
    -0.10
    erc
    -0.09
    erce
    -0.09
    erm
    -0.08
    heimer
    -0.08
    hic
    -0.08
    icum
    -0.08
     spur
    -0.08
    eed
    -0.08
     Jude
    -0.07
    POSITIVE LOGITS
    ser
    0.16
    ible
    0.13
    ibility
    0.13
    iveness
    0.12
    ivity
    0.12
    IBLE
    0.11
    sock
    0.11
    IBILITY
    0.11
    ibles
    0.11
    ibilities
    0.10
    Activations Density 0.020%

    No Known Activations