© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    read more

    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
    phans
    -0.12
    eping
    -0.11
    inine
    -0.10
    swith
    -0.10
    ustralian
    -0.10
    ses
    -0.10
    OrFail
    -0.10
    ients
    -0.10
    lsx
    -0.10
    tures
    -0.09
    POSITIVE LOGITS
    gether
    0.43
    tempts
    0.29
    bidden
    0.28
    jourd
    0.28
    adays
    0.28
    etheless
    0.26
    theless
    0.25
    bsites
    0.25
    nger
    0.25
    htable
    0.23
    Activations Density 2.001%

    No Known Activations