© 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. 47975
    Prev
    Next
    INDEX
    Explanations

    heard someone say

    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
     smile
    -0.11
    azi
    -0.10
     smiles
    -0.10
    া
    -0.10
     smiling
    -0.10
    lights
    -0.10
    avn
    -0.09
    Installer
    -0.09
    atz
    -0.09
     Bog
    -0.09
    POSITIVE LOGITS
     conversations
    0.31
     conversation
    0.30
     Convers
    0.22
     discussions
    0.22
    Conversation
    0.21
     discussion
    0.20
     discussing
    0.20
    conversation
    0.20
     Conversation
    0.20
     convers
    0.20
    Activations Density 0.058%

    No Known Activations