© 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. 31672
    Prev
    Next
    INDEX
    Explanations

    Have followed by questions or phrases

    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
     wink
    -0.08
    INET
    -0.08
     conce
    -0.07
     robust
    -0.07
    ²
    -0.07
    inet
    -0.07
     Champ
    -0.07
    wd
    -0.06
    ORT
    -0.06
     flush
    -0.06
    POSITIVE LOGITS
     mercy
    0.13
     faith
    0.12
     courage
    0.12
     patience
    0.12
     ~~
    0.12
    ipro
    0.12
     pity
    0.11
     confidence
    0.10
    faith
    0.10
     Mime
    0.10
    Activations Density 0.007%

    No Known Activations