© 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. 117132
    Prev
    Next
    INDEX
    Explanations

    discussion topics

    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
     Craigslist
    -0.13
     hookup
    -0.12
     nightlife
    -0.11
     vet
    -0.11
     grass
    -0.10
     searching
    -0.10
     positives
    -0.10
     recip
    -0.10
     desperation
    -0.10
     favorable
    -0.10
    POSITIVE LOGITS
     chat
    0.14
     topics
    0.13
     discussion
    0.12
    -chat
    0.12
     fascinating
    0.12
     discussing
    0.12
    interactive
    0.12
     interactive
    0.12
     chatting
    0.12
     conversation
    0.12
    Activations Density 0.002%

    No Known Activations