© 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. 31740
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     Dann
    -0.12
     Cord
    -0.12
    ÄĻ
    -0.11
     Kee
    -0.11
     cerv
    -0.11
     cervical
    -0.11
     Bair
    -0.11
     Steele
    -0.11
    ittel
    -0.10
     Nelson
    -0.10
    POSITIVE LOGITS
    26
    0.35
    27
    0.34
    28
    0.27
    25
    0.23
    026
    0.21
    29
    0.19
    027
    0.18
    266
    0.16
    24
    0.16
    261
    0.16
    Activations Density 0.270%

    No Known Activations