© 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. 26642
    Prev
    Next
    INDEX
    Explanations

    would wish

    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
     prima
    -0.10
     brag
    -0.08
    egen
    -0.08
     readily
    -0.08
     potentially
    -0.07
     initially
    -0.07
    rag
    -0.07
     laugh
    -0.07
     TA
    -0.07
    emas
    -0.07
    POSITIVE LOGITS
     hurry
    0.27
     haste
    0.17
     PLEASE
    0.17
     hurried
    0.14
     please
    0.14
     somehow
    0.14
    Please
    0.14
     sooner
    0.14
     mirac
    0.14
    PLEASE
    0.13
    Activations Density 0.032%

    No Known Activations