© 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. 6695
    Prev
    Next
    INDEX
    Explanations

    wrapping and enclosing

    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
    oppable
    -0.11
    ampp
    -0.10
    edis
    -0.10
     Cummings
    -0.10
    iq
    -0.10
    atu
    -0.10
    gui
    -0.10
    esa
    -0.10
    uba
    -0.09
    chang
    -0.09
    POSITIVE LOGITS
     arms
    0.12
     strands
    0.10
    strand
    0.10
    arms
    0.10
     mono
    0.10
    stile
    0.10
     Arms
    0.09
    _arm
    0.09
     herself
    0.09
     himself
    0.09
    Activations Density 0.003%

    No Known Activations