© 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. 113965
    Prev
    Next
    INDEX
    Explanations

    NA/HA/MA/PA syllables

    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
    s
    -0.27
    NI
    -0.17
    TS
    -0.17
    TH
    -0.17
    DA
    -0.16
    NS
    -0.16
    TF
    -0.16
    TL
    -0.16
    DC
    -0.16
    TA
    -0.16
    POSITIVE LOGITS
    o
    0.14
    st
    0.14
    mp
    0.14
    de
    0.13
    re
    0.13
    men
    0.12
    mb
    0.12
    ging
    0.12
    ting
    0.12
    cy
    0.12
    Activations Density 0.528%

    No Known Activations