© 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. 26493
    Prev
    Next
    INDEX
    Explanations

    audience, do, crime, cookies, chemistry, our

    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
     IMO
    -0.09
    ect
    -0.09
     arguably
    -0.08
     feas
    -0.08
    iter
    -0.08
     Marr
    -0.08
     ful
    -0.08
    ãģĿ
    -0.07
    cz
    -0.07
     vi
    -0.07
    POSITIVE LOGITS
     vo
    0.11
     FW
    0.10
    md
    0.10
     Gem
    0.10
    VO
    0.10
    ODY
    0.10
    pla
    0.10
     Robertson
    0.10
     Kem
    0.09
     Roh
    0.09
    Activations Density 0.347%

    No Known Activations