© 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. 3697
    Prev
    Next
    INDEX
    Explanations

    dirt and hands

    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
     Dome
    -0.12
     Vac
    -0.11
     Gall
    -0.11
     dome
    -0.10
     gall
    -0.10
    ilar
    -0.10
    fen
    -0.10
    THON
    -0.09
     topp
    -0.09
    aval
    -0.09
    POSITIVE LOGITS
     dirty
    0.31
     cleanliness
    0.29
     dirt
    0.28
     clean
    0.28
     Dirty
    0.25
     CLEAN
    0.24
     Clean
    0.24
    dirty
    0.24
    Clean
    0.23
     washing
    0.23
    Activations Density 0.168%

    No Known Activations