© 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. 33253
    Prev
    Next
    INDEX
    Explanations

    whole page or full content

    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
    	strncpy
    -0.09
     Feinstein
    -0.08
    ackers
    -0.08
    ettel
    -0.08
    олÑĥÑĩ
    -0.08
     alcuni
    -0.08
    jang
    -0.08
    ilde
    -0.08
    redd
    -0.08
     ess
    -0.08
    POSITIVE LOGITS
     entire
    0.70
     full
    0.63
     whole
    0.62
     entirety
    0.61
     Entire
    0.59
     complete
    0.53
    åħ¨éĥ¨
    0.52
    whole
    0.50
     FULL
    0.50
    Whole
    0.46
    Activations Density 1.481%

    No Known Activations