© 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. 116606
    Prev
    Next
    INDEX
    Explanations

    software, free, push, ago

    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
     Cruz
    -0.10
     accessor
    -0.10
     Pope
    -0.10
     blinking
    -0.10
     Gren
    -0.10
     Denn
    -0.10
    /Form
    -0.10
     touching
    -0.09
     Blink
    -0.09
     Slice
    -0.09
    POSITIVE LOGITS
     remark
    0.10
     minor
    0.10
     ner
    0.09
    -fit
    0.09
     bund
    0.09
     sit
    0.09
     away
    0.09
    (push
    0.08
    acad
    0.08
    ayette
    0.08
    Activations Density 0.007%

    No Known Activations