© 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. 113121
    Prev
    Next
    INDEX
    Explanations

    step-by-step instructions or guides

    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
     tipping
    -0.11
    ambre
    -0.11
    mare
    -0.10
    akk
    -0.10
     ë¶Ģ
    -0.10
     speeding
    -0.09
    isse
    -0.09
    edef
    -0.09
    NCY
    -0.09
     Patterns
    -0.09
    POSITIVE LOGITS
     step
    0.27
     steps
    0.26
     guide
    0.24
    -step
    0.24
    æŃ¥
    0.24
    step
    0.21
     instructions
    0.21
     Step
    0.21
     Steps
    0.21
     guides
    0.21
    Activations Density 0.145%

    No Known Activations