© 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. 4541
    Prev
    Next
    INDEX
    Explanations

    Suffixes like -ent, -ant, -ment

    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
    head
    -0.13
    holder
    -0.11
    s
    -0.11
    leen
    -0.11
    headed
    -0.10
    ington
    -0.10
    ingly
    -0.10
    orld
    -0.10
    bie
    -0.10
    idable
    -0.09
    POSITIVE LOGITS
    emente
    0.25
    ia
    0.17
    ials
    0.16
    iation
    0.16
    ium
    0.16
    ially
    0.15
    ial
    0.15
    cies
    0.15
    cy
    0.15
    iae
    0.14
    Activations Density 0.379%

    No Known Activations