© 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. 113215
    Prev
    Next
    INDEX
    Explanations

    needs and preferences

    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
     pole
    -0.11
    ocker
    -0.10
    oes
    -0.10
    ynos
    -0.10
    apol
    -0.09
    mo
    -0.09
     universally
    -0.09
    Canonical
    -0.09
     Tag
    -0.09
     mo
    -0.09
    POSITIVE LOGITS
    erie
    0.10
     Carey
    0.09
     McCoy
    0.09
    oland
    0.09
     Prest
    0.09
     Hammond
    0.08
    incer
    0.08
    лÑĮ
    0.08
    /preferences
    0.08
     muster
    0.08
    Activations Density 0.007%

    No Known Activations