© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    new text prompts

    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
     Alonso
    -0.11
    .look
    -0.10
     balk
    -0.10
     look
    -0.09
     Look
    -0.09
     pup
    -0.09
    asa
    -0.09
     alph
    -0.09
     LOOK
    -0.09
     lookup
    -0.09
    POSITIVE LOGITS
     louder
    0.11
     spur
    0.11
     spurred
    0.11
     motivating
    0.10
     encouragement
    0.10
    Apparently
    0.10
     motivated
    0.10
     repetitions
    0.10
     apparently
    0.09
    words
    0.09
    Activations Density 0.019%

    No Known Activations