© 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. 48031
    Prev
    Next
    INDEX
    Explanations

    Vint, Vredenburg, Vinchopolis, Vrtunski

    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
    IGO
    -0.10
     stri
    -0.10
     shaving
    -0.09
    atat
    -0.09
    iedad
    -0.09
     Sach
    -0.09
    illi
    -0.09
    arily
    -0.09
     herr
    -0.09
    ilee
    -0.09
    POSITIVE LOGITS
     eve
    0.10
     devastating
    0.09
     dirt
    0.08
     Foreign
    0.08
    roys
    0.08
    emm
    0.08
    ponential
    0.08
     rush
    0.08
     Bass
    0.07
     guarantee
    0.07
    Activations Density 0.187%

    No Known Activations