© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18211
    Prev
    Next
    INDEX
    Explanations

    leaving or stopping

    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
    740
    -0.11
     Bog
    -0.10
    еб
    -0.09
    orda
    -0.09
     Mate
    -0.09
     enclosed
    -0.09
    éra
    -0.09
     Nationwide
    -0.09
    Mate
    -0.09
     gamble
    -0.09
    POSITIVE LOGITS
     plans
    0.11
     sacrificing
    0.10
     Sacr
    0.10
     sacrificed
    0.10
     inorder
    0.10
     vacation
    0.10
     sacrifice
    0.10
     specially
    0.10
     Plans
    0.10
     accordingly
    0.09
    Activations Density 0.177%

    No Known Activations