© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    catch or capture

    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
    vip
    -0.11
     degrade
    -0.11
     unlink
    -0.11
    HIR
    -0.11
     erased
    -0.11
     degraded
    -0.11
     Shard
    -0.11
    _shuffle
    -0.11
    flen
    -0.11
     Kub
    -0.10
    POSITIVE LOGITS
     capture
    0.63
     Capture
    0.58
     capturing
    0.57
     captures
    0.54
    Capture
    0.51
    capture
    0.50
     captured
    0.48
    captures
    0.39
    _capture
    0.39
     Capt
    0.38
    Activations Density 0.350%

    No Known Activations