© 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. 91493
    Prev
    Next
    INDEX
    Explanations

    slip or slipping into something

    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
     Dirt
    -0.10
     Rug
    -0.09
     Wort
    -0.09
     intimately
    -0.09
     Maurice
    -0.09
     Zu
    -0.09
    pike
    -0.08
    à¹Į
    -0.08
    /Page
    -0.08
    ·¸
    -0.08
    POSITIVE LOGITS
     unnoticed
    0.12
    perl
    0.10
     slipped
    0.10
     Tonight
    0.09
     unc
    0.09
     grasp
    0.09
     away
    0.09
     slipping
    0.09
     into
    0.09
     invol
    0.09
    Activations Density 0.016%

    No Known Activations