© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6498
    Prev
    Next
    INDEX
    Explanations

    Pokemon, however, types

    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
     lesbian
    -0.12
     NPR
    -0.10
    abbo
    -0.10
     Lesbian
    -0.09
     LGBT
    -0.09
     aun
    -0.09
     GURL
    -0.09
     âĻ¥
    -0.09
    bery
    -0.08
     Kathryn
    -0.08
    POSITIVE LOGITS
     IGN
    0.12
    ault
    0.12
     Bench
    0.11
     Cout
    0.11
     bang
    0.11
     Montreal
    0.10
     Gon
    0.10
    DFS
    0.10
     stag
    0.10
     progn
    0.10
    Activations Density 0.050%

    No Known Activations