© 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. 5250
    Prev
    Next
    INDEX
    Explanations

    "don't" followed by verbs

    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
     Bernstein
    -0.10
     Salvador
    -0.10
     reputed
    -0.09
     fractured
    -0.09
    Began
    -0.08
     Cummings
    -0.08
    /read
    -0.08
     Erick
    -0.08
    ms
    -0.08
    iska
    -0.08
    POSITIVE LOGITS
     mater
    0.14
     worry
    0.14
     TOUCH
    0.12
     touch
    0.12
     Touch
    0.12
     patron
    0.11
     Fence
    0.10
     worried
    0.10
     mention
    0.10
     critic
    0.10
    Activations Density 0.010%

    No Known Activations