© 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. 16228
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    Also
    -0.10
     also
    -0.09
    ëŀ
    -0.09
    Mate
    -0.09
     Dover
    -0.09
    578
    -0.09
    еÑģÑĤв
    -0.08
    rating
    -0.08
    aving
    -0.08
     Also
    -0.08
    POSITIVE LOGITS
     meanwhile
    0.32
     Meanwhile
    0.23
     meantime
    0.21
    Meanwhile
    0.20
     moreover
    0.16
     furthermore
    0.14
     part
    0.13
     myself
    0.11
     FW
    0.10
    DMI
    0.10
    Activations Density 0.051%

    No Known Activations