© 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. 33418
    Prev
    Next
    INDEX
    Explanations

    enjoyment and pleasantness

    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
     gravitational
    -0.11
    uya
    -0.11
    ario
    -0.10
    emic
    -0.10
     Urg
    -0.09
    ç¬
    -0.09
    verbosity
    -0.09
     apost
    -0.09
     industri
    -0.09
    acity
    -0.09
    POSITIVE LOGITS
     enjoyment
    0.38
     enjoyable
    0.37
     Enjoy
    0.34
     enjoying
    0.33
     enjoy
    0.32
    Enjoy
    0.31
     enjoyed
    0.30
     enjoys
    0.26
    享
    0.20
     pleasant
    0.19
    Activations Density 0.094%

    No Known Activations