© 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. 89730
    Prev
    Next
    INDEX
    Explanations

    use of time condition

    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
     Ing
    -0.10
    aj
    -0.09
    bring
    -0.09
    els
    -0.09
    asm
    -0.09
     conc
    -0.09
    var
    -0.09
    OI
    -0.09
     treat
    -0.08
    icals
    -0.08
    POSITIVE LOGITS
     flank
    0.10
     acompan
    0.10
     Peek
    0.10
     repe
    0.09
     sez
    0.09
     Sle
    0.09
     wre
    0.08
     thumbs
    0.08
     evacuated
    0.08
     worst
    0.08
    Activations Density 0.001%

    No Known Activations