© 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. 50336
    Prev
    Next
    INDEX
    Explanations

    questions about what

    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
    uye
    -0.10
    ..↵↵↵↵
    -0.09
    oser
    -0.09
     traps
    -0.09
    pai
    -0.09
    oker
    -0.09
     invers
    -0.08
    czy
    -0.08
    enger
    -0.08
     Wich
    -0.08
    POSITIVE LOGITS
    italic
    0.14
     tribute
    0.09
     Hands
    0.09
     Repos
    0.09
     Actress
    0.09
    rex
    0.09
     Cont
    0.09
    Millis
    0.08
    chn
    0.08
     chic
    0.08
    Activations Density 0.014%

    No Known Activations