© 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. 92436
    Prev
    Next
    INDEX
    Explanations

    list of items or concepts

    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
     atleast
    -0.15
     thru
    -0.14
     alot
    -0.13
     whilst
    -0.13
     “âĢ¦
    -0.13
     seper
    -0.13
     retarded
    -0.12
     homosexuals
    -0.12
     ‘
    -0.12
    uely
    -0.12
    POSITIVE LOGITS
    —and
    0.26
     —
    0.23
     luxe
    0.22
     probs
    0.21
    —or
    0.21
     ÂŃ
    0.21
    —you
    0.21
    —but
    0.20
     rej
    0.20
     GIF
    0.18
    Activations Density 2.458%

    No Known Activations