© 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. 18189
    Prev
    Next
    INDEX
    Explanations

    visual media

    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
     Cra
    -0.10
     verbally
    -0.10
     brakes
    -0.09
     benef
    -0.09
     deadlines
    -0.09
     receptors
    -0.09
    Newsletter
    -0.09
     fate
    -0.09
    oves
    -0.09
    _roles
    -0.08
    POSITIVE LOGITS
     footage
    0.38
     photographs
    0.35
     videos
    0.35
     pictures
    0.34
     screenshots
    0.33
     images
    0.33
     photos
    0.32
     snapshots
    0.31
     recordings
    0.28
     photograph
    0.26
    Activations Density 1.696%

    No Known Activations