© 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. 15908
    Prev
    Next
    INDEX
    Explanations

    tagging, chipping, masking

    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
    lev
    -0.11
    ily
    -0.11
    SELL
    -0.10
    wit
    -0.10
     lev
    -0.10
    ington
    -0.10
     levy
    -0.09
     tact
    -0.09
    resses
    -0.09
     Sham
    -0.09
    POSITIVE LOGITS
    /tag
    0.12
     prepar
    0.11
     together
    0.11
     snug
    0.11
    -Un
    0.09
     Together
    0.09
     securely
    0.09
     Teh
    0.09
    arlo
    0.09
     equipped
    0.08
    Activations Density 0.081%

    No Known Activations