© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6293
    Prev
    Next
    INDEX
    Explanations

    asking "anyone" questions

    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
     Kahn
    -0.07
    lac
    -0.07
     Dear
    -0.07
     lad
    -0.07
    Ĥ
    -0.07
     hem
    -0.07
     Sommer
    -0.06
     darling
    -0.06
     wal
    -0.06
    oral
    -0.06
    POSITIVE LOGITS
     ever
    0.24
     anything
    0.21
     anymore
    0.21
     gonna
    0.20
     any
    0.20
     EVER
    0.18
    ?č↵
    0.18
    ?</
    0.18
    ?↵↵↵
    0.18
     able
    0.17
    Activations Density 0.156%

    No Known Activations