© 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. 7474
    Prev
    Next
    INDEX
    Explanations

    is equivalent to

    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
    (mon
    -0.11
    arda
    -0.11
    orge
    -0.10
    DON
    -0.10
    vk
    -0.09
     hor
    -0.09
     reap
    -0.09
     subscript
    -0.09
    oline
    -0.09
    NEY
    -0.09
    POSITIVE LOGITS
     tant
    0.16
     знаÑĩ
    0.11
     equivalent
    0.11
     to
    0.10
     acknowledging
    0.10
     akin
    0.10
     misunder
    0.10
    	to
    0.10
     Equivalent
    0.09
    "To
    0.09
    Activations Density 0.039%

    No Known Activations