© 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. 48353
    Prev
    Next
    INDEX
    Explanations

    following "so"

    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
    æĪij
    -0.10
    Personally
    -0.09
     Stanton
    -0.09
    SL
    -0.08
     warrants
    -0.08
    520
    -0.08
    521
    -0.08
    inha
    -0.08
     integrated
    -0.08
     Personally
    -0.08
    POSITIVE LOGITS
     send
    0.15
     if
    0.14
     Contact
    0.14
     contact
    0.14
     Send
    0.13
     come
    0.13
     gim
    0.13
     If
    0.13
     anyone
    0.13
    send
    0.13
    Activations Density 0.024%

    No Known Activations