© 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. 16564
    Prev
    Next
    INDEX
    Explanations

    transmission, trackers, transmit, roid, Tony

    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
    ively
    -0.11
    ï¸ı
    -0.11
    ures
    -0.11
    hips
    -0.11
    elo
    -0.10
    ingly
    -0.10
    pine
    -0.10
    avin
    -0.10
    pliers
    -0.09
    imenti
    -0.09
    POSITIVE LOGITS
    trash
    0.11
    -led
    0.10
     trash
    0.10
    -dominated
    0.09
     peace
    0.09
    tran
    0.09
     rights
    0.09
     killer
    0.09
     tossing
    0.09
     tran
    0.09
    Activations Density 0.001%

    No Known Activations