© 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. 15944
    Prev
    Next
    INDEX
    Explanations

    revival of interest

    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
     Moody
    -0.10
     replacement
    -0.10
    Replacement
    -0.10
     Replacement
    -0.09
    replacement
    -0.09
    chg
    -0.09
     reversible
    -0.09
     irreversible
    -0.09
     anymore
    -0.08
    ìŀIJ
    -0.08
    POSITIVE LOGITS
     vigor
    0.15
     fortunes
    0.14
     acquaintance
    0.14
     old
    0.13
     lost
    0.13
    -old
    0.13
     vig
    0.12
     dormant
    0.12
     forgotten
    0.12
     interrupted
    0.12
    Activations Density 0.205%

    No Known Activations