© 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. 113878
    Prev
    Next
    INDEX
    Explanations

    ing/ers/e/eed/ered/eering

    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
    urg
    -0.10
    ẩ
    -0.09
    amm
    -0.09
    ê¹
    -0.09
     overhe
    -0.08
     ear
    -0.08
     prefixed
    -0.08
    cope
    -0.08
    urger
    -0.08
    clerosis
    -0.08
    POSITIVE LOGITS
    ers
    0.22
    e
    0.21
    eed
    0.17
    ered
    0.16
    eo
    0.16
    ele
    0.16
    ering
    0.15
    tion
    0.15
    een
    0.15
    ein
    0.15
    Activations Density 0.001%

    No Known Activations