© 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. 26945
    Prev
    Next
    INDEX
    Explanations

    Tulane, Tulbagh, tulipy, Tullie, Stadtspital

    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
     Cunning
    -0.08
    throp
    -0.08
    ì¹ĺ
    -0.07
    ossa
    -0.07
    mont
    -0.07
     fork
    -0.07
     Islamabad
    -0.07
    minster
    -0.07
    page
    -0.07
    leh
    -0.07
    POSITIVE LOGITS
     EAR
    0.12
    олов
    0.11
    ctica
    0.11
     sexes
    0.11
     shy
    0.10
    Barrier
    0.10
     Bair
    0.10
     Parcel
    0.10
    licas
    0.10
    hotel
    0.10
    Activations Density 0.001%

    No Known Activations