© 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. 26120
    Prev
    Next
    INDEX
    Explanations

    try to + verb

    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
    chten
    -0.13
     attempt
    -0.12
    attempt
    -0.12
     Attempts
    -0.12
     attempts
    -0.12
     sadly
    -0.11
    rete
    -0.11
     Kut
    -0.11
     sharpen
    -0.11
    utar
    -0.11
    POSITIVE LOGITS
     always
    0.14
     whenever
    0.11
     never
    0.10
    always
    0.10
     Always
    0.10
     maxim
    0.10
     balanced
    0.10
     balance
    0.10
    oa
    0.09
     avoid
    0.09
    Activations Density 0.170%

    No Known Activations