© 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. 88297
    Prev
    Next
    INDEX
    Explanations

    what leading to cause

    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
    uci
    -0.10
    acr
    -0.10
     outfits
    -0.10
     cif
    -0.10
     revolving
    -0.10
     Hutchinson
    -0.10
     Peg
    -0.10
     Mej
    -0.10
    Asked
    -0.10
    pj
    -0.10
    POSITIVE LOGITS
     causing
    0.12
     cause
    0.11
     culprit
    0.11
    cause
    0.09
    -ca
    0.09
     inducing
    0.08
     ca
    0.08
     Richards
    0.08
     lest
    0.08
     caused
    0.08
    Activations Density 0.009%

    No Known Activations