© 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. 4999
    Prev
    Next
    INDEX
    Explanations

    personal growth and experience

    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
     usually
    -0.12
     apparently
    -0.11
     yourself
    -0.11
     potentially
    -0.11
    you
    -0.10
     presumably
    -0.10
    ä½ł
    -0.10
    unless
    -0.10
     normally
    -0.10
     disturb
    -0.09
    POSITIVE LOGITS
     helped
    0.24
     taught
    0.19
     invaluable
    0.17
     my
    0.17
    æĪijçļĦ
    0.16
     gave
    0.16
     initially
    0.15
     transformative
    0.15
     enabled
    0.14
     unexpected
    0.14
    Activations Density 0.295%

    No Known Activations