© 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. 28646
    Prev
    Next
    INDEX
    Explanations

    -ize, -ify, -elicit, -forestall

    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
     took
    -0.12
     can
    -0.12
     gave
    -0.12
     drew
    -0.12
     went
    -0.11
     could
    -0.11
     would
    -0.11
     will
    -0.11
     are
    -0.10
    äºĨ
    -0.10
    POSITIVE LOGITS
    itize
    0.18
     be
    0.18
    ize
    0.16
    iliate
    0.16
    imize
    0.16
    italize
    0.16
    ify
    0.15
    аÑĤÑĮ
    0.15
     become
    0.14
    isify
    0.14
    Activations Density 0.210%

    No Known Activations