© 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. 27187
    Prev
    Next
    INDEX
    Explanations

    entire body, throughout, diffuse, generalized

    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
     surrounding
    -0.10
    ITS
    -0.10
     Component
    -0.09
    ège
    -0.09
     components
    -0.09
     "><
    -0.09
    MODE
    -0.09
     Breast
    -0.09
    äs
    -0.09
     série
    -0.09
    POSITIVE LOGITS
     entire
    0.13
    /body
    0.12
     simult
    0.11
     body
    0.11
     simultaneous
    0.10
     Giz
    0.10
     systemic
    0.10
     simultaneously
    0.10
     systematic
    0.10
     Prem
    0.09
    Activations Density 0.101%

    No Known Activations