© 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. 16246
    Prev
    Next
    INDEX
    Explanations

    functionality requirements and inclusions

    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
     Bedrooms
    -0.10
     Wrapped
    -0.08
    -sale
    -0.08
    Bes
    -0.08
    /slick
    -0.08
     Tickets
    -0.08
     Exiting
    -0.07
     unl
    -0.07
     needless
    -0.07
     Behind
    -0.07
    POSITIVE LOGITS
     Includes
    0.25
    Includes
    0.25
     Requires
    0.23
     May
    0.23
     includes
    0.23
     requires
    0.22
    Requires
    0.22
    Provides
    0.21
     Allows
    0.21
     contains
    0.21
    Activations Density 0.610%

    No Known Activations