© 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. 16108
    Prev
    Next
    INDEX
    Explanations

    particular wireless

    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
    %(
    -0.09
    atum
    -0.09
    gest
    -0.09
    paged
    -0.09
     Mund
    -0.08
     USC
    -0.08
     side
    -0.08
    inka
    -0.08
     promot
    -0.08
    estr
    -0.08
    POSITIVE LOGITS
     dear
    0.11
     Zah
    0.11
    Dear
    0.11
     Ashe
    0.11
     Dear
    0.10
    Looking
    0.09
    trs
    0.09
    eling
    0.09
     nag
    0.09
     Shannon
    0.09
    Activations Density 0.001%

    No Known Activations