© 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. 28853
    Prev
    Next
    INDEX
    Explanations

    slip, slid, slipping, session, alcohol

    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
     Chow
    -0.12
     Chap
    -0.11
     Gaines
    -0.10
     Chuck
    -0.10
     chap
    -0.09
     Wheat
    -0.09
     Passing
    -0.09
    ddb
    -0.09
     Ezra
    -0.09
     resh
    -0.09
    POSITIVE LOGITS
     bak
    0.10
     conscious
    0.09
     dying
    0.09
    æ²»
    0.09
     Pearl
    0.09
    unic
    0.09
     veterans
    0.08
     aroused
    0.08
     slowly
    0.08
    /sl
    0.08
    Activations Density 0.005%

    No Known Activations