© 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. 31396
    Prev
    Next
    INDEX
    Explanations

    seeking information or solutions

    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
     primitives
    -0.09
     subpoena
    -0.08
    éri
    -0.08
    issions
    -0.08
    asa
    -0.08
    Ñı
    -0.08
     nieuwe
    -0.08
    ası
    -0.08
     satellites
    -0.08
    DH
    -0.08
    POSITIVE LOGITS
     articles
    0.33
     blogs
    0.29
     online
    0.29
     forums
    0.26
     websites
    0.25
     blog
    0.23
    articles
    0.23
     literature
    0.23
     reports
    0.22
     Blogs
    0.22
    Activations Density 1.314%

    No Known Activations