© 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. 48504
    Prev
    Next
    INDEX
    Explanations

    garbage, blepharoptosis, bleomycin

    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
    ency
    -0.09
    glas
    -0.08
    filled
    -0.08
     Overflow
    -0.08
    erset
    -0.08
     naked
    -0.08
     overflow
    -0.08
     filled
    -0.08
    ENCY
    -0.08
    IZER
    -0.08
    POSITIVE LOGITS
    edo
    0.12
     disguise
    0.11
    utas
    0.11
     selections
    0.11
    orra
    0.11
    urb
    0.10
     Prote
    0.10
     discern
    0.10
     Darling
    0.10
    indr
    0.10
    Activations Density 0.004%

    No Known Activations