© 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. 49594
    Prev
    Next
    INDEX
    Explanations

    following everything else

    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
     oft
    -0.10
     sometimes
    -0.10
    ipel
    -0.09
    Sometimes
    -0.09
     recently
    -0.09
    yna
    -0.09
    izo
    -0.08
     Sometimes
    -0.08
     outright
    -0.08
    udd
    -0.08
    POSITIVE LOGITS
     subsequent
    0.16
     everything
    0.15
    everything
    0.12
    sequent
    0.11
     Everything
    0.11
    Everything
    0.11
     meetings
    0.10
    meet
    0.10
     Meeting
    0.10
     conversations
    0.10
    Activations Density 0.058%

    No Known Activations