© 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. 47274
    Prev
    Next
    INDEX
    Explanations

    technical terms, commercial, genetic, infections

    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
    yna
    -0.11
     bist
    -0.10
    ouse
    -0.10
     Constr
    -0.10
    drs
    -0.09
     retirement
    -0.09
    æķ
    -0.09
    onga
    -0.09
     Tir
    -0.09
     DRV
    -0.09
    POSITIVE LOGITS
    ophobia
    0.09
    593
    0.09
    ffffffff
    0.08
     Noon
    0.08
     Globe
    0.08
    æŀ
    0.08
     globe
    0.08
    RING
    0.08
     Asc
    0.08
    ÙĦÙī
    0.08
    Activations Density 0.001%

    No Known Activations