© 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. 16587
    Prev
    Next
    INDEX
    Explanations

    normalizing, normalising, normal, normotensive

    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
    ward
    -0.10
    rière
    -0.10
    ed
    -0.09
    riere
    -0.09
    elow
    -0.09
    DAQ
    -0.09
    eral
    -0.09
    quake
    -0.09
    ÑĢа
    -0.09
    entimes
    -0.09
    POSITIVE LOGITS
    ity
    0.28
    cy
    0.26
    izing
    0.21
    cies
    0.19
    ised
    0.19
    mente
    0.19
    ITY
    0.17
    ities
    0.17
    isation
    0.17
    izedName
    0.17
    Activations Density 0.104%

    No Known Activations