© 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. 117335
    Prev
    Next
    INDEX
    Explanations

    CS followed by numbers or .js

    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
    ieu
    -0.12
    eren
    -0.10
     Stanton
    -0.09
    pai
    -0.09
    ìłľ
    -0.09
     Maid
    -0.08
    engo
    -0.08
     undef
    -0.08
     Aires
    -0.08
     escal
    -0.08
    POSITIVE LOGITS
    abus
    0.10
    .brand
    0.09
    osit
    0.09
     Techn
    0.09
     bone
    0.09
    retain
    0.09
    enger
    0.09
    isman
    0.09
     Ends
    0.09
     spun
    0.09
    Activations Density 0.007%

    No Known Activations