© 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. 6508
    Prev
    Next
    INDEX
    Explanations

    show youshow meshowed youshowed me

    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
     hon
    -0.11
    testing
    -0.11
    upp
    -0.10
    ancia
    -0.10
     wing
    -0.10
     refinement
    -0.10
    acc
    -0.10
     Hon
    -0.10
     Testing
    -0.10
     testing
    -0.09
    POSITIVE LOGITS
     show
    0.13
     SHOW
    0.12
    -show
    0.12
    show
    0.11
     showed
    0.10
     Show
    0.10
    Show
    0.10
     Preferred
    0.10
    	show
    0.10
     shows
    0.09
    Activations Density 0.031%

    No Known Activations