© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33874
    Prev
    Next
    INDEX
    Explanations

    logical and formal structuring

    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
    /person
    -0.13
     ðŁĴ
    -0.12
    ðŁĴ
    -0.12
     groom
    -0.12
     unhealthy
    -0.12
    comfort
    -0.12
    âĻ¥
    -0.12
     lifestyle
    -0.12
     âĿ¤
    -0.12
    /people
    -0.11
    POSITIVE LOGITS
    è¿°
    0.10
     explicitly
    0.09
     diagram
    0.09
     logically
    0.09
     latina
    0.09
     applicable
    0.09
     diagrams
    0.09
     narrowly
    0.08
     theoretically
    0.08
     explicit
    0.08
    Activations Density 13.398%

    No Known Activations