© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    Japanese company names/descriptions

    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
     Sail
    -0.10
     collo
    -0.10
    fire
    -0.09
    gend
    -0.09
     lace
    -0.09
     Cunningham
    -0.09
    osti
    -0.09
     Hera
    -0.09
    /groups
    -0.09
    lace
    -0.09
    POSITIVE LOGITS
    åĻ¨
    0.14
    ìłģ
    0.13
    èĢħ
    0.13
    0.11
    æĢ§
    0.11
    çīĪ
    0.10
    ãģĹãģŁ
    0.10
    ëIJľ
    0.10
    åŀĭ
    0.09
     phẩm
    0.09
    Activations Density 0.116%

    No Known Activations