© 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. 112015
    Prev
    Next
    INDEX
    Explanations

    tips for advice

    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
     Ner
    -0.14
     latch
    -0.11
    erde
    -0.11
     Vine
    -0.11
     Zwe
    -0.11
     plat
    -0.10
     Stap
    -0.10
    bff
    -0.10
    ÑĮ
    -0.10
     franç
    -0.10
    POSITIVE LOGITS
    /ad
    0.12
     tips
    0.11
    /tr
    0.10
     given
    0.10
    Tip
    0.10
    /rules
    0.10
    geber
    0.09
     Tip
    0.09
     tip
    0.09
    tips
    0.09
    Activations Density 0.047%

    No Known Activations