© 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. 117528
    Prev
    Next
    INDEX
    Explanations

    projecting or projection

    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
    lore
    -0.12
    nect
    -0.11
    Ãłng
    -0.11
    ioned
    -0.10
    observable
    -0.10
    yan
    -0.10
    segue
    -0.10
     Depot
    -0.10
     Igor
    -0.10
     shipped
    -0.10
    POSITIVE LOGITS
     onto
    0.25
    onto
    0.16
     shadow
    0.13
     projecting
    0.13
     projection
    0.12
    shadow
    0.11
     Ont
    0.11
     holog
    0.10
     projected
    0.10
     shadows
    0.10
    Activations Density 0.117%

    No Known Activations