© 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. 4009
    Prev
    Next
    INDEX
    Explanations

    quality award brand

    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
     preach
    -0.11
     pomp
    -0.11
     Lazar
    -0.10
     intolerance
    -0.10
     sensory
    -0.10
     Passion
    -0.10
    antro
    -0.09
    anches
    -0.09
     quat
    -0.09
     Pols
    -0.09
    POSITIVE LOGITS
     smile
    0.39
     smiles
    0.35
     smiling
    0.32
     smiled
    0.31
     Smile
    0.30
     grin
    0.24
     smirk
    0.17
    ç¬ij
    0.17
     grinned
    0.17
     SM
    0.16
    Activations Density 0.098%

    No Known Activations