© 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. 27581
    Prev
    Next
    INDEX
    Explanations

    saying "more information"

    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
     deb
    -0.10
     Jeb
    -0.09
     Harris
    -0.08
     Sab
    -0.08
     next
    -0.08
     distressed
    -0.08
    aoke
    -0.08
    SK
    -0.08
    ogens
    -0.08
     BBQ
    -0.08
    POSITIVE LOGITS
     see
    0.12
     information
    0.12
    ä¿¡æģ¯
    0.11
     whatsoever
    0.11
    information
    0.11
     ado
    0.11
    /details
    0.11
    ixa
    0.10
    fal
    0.10
     REFER
    0.10
    Activations Density 0.069%

    No Known Activations