© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25011
    Prev
    Next
    INDEX
    Explanations

    subjective experience and description

    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
    Negative Logits
    acha
    -0.13
     blames
    -0.11
     curs
    -0.11
     scoreboard
    -0.11
     consum
    -0.11
    xon
    -0.11
     blaming
    -0.11
    outil
    -0.11
     blame
    -0.11
     accuse
    -0.10
    POSITIVE LOGITS
     sensations
    0.29
     descriptions
    0.28
     sensation
    0.26
     subjective
    0.25
     description
    0.24
     experience
    0.24
     experiences
    0.23
     describe
    0.23
     Experience
    0.23
     describing
    0.21
    Activations Density 0.172%

    No Known Activations