© 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. 113675
    Prev
    Next
    INDEX
    Explanations

    HD quality video and visuals

    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
     flavored
    -0.12
     BX
    -0.12
     disguised
    -0.11
     unconventional
    -0.11
     ming
    -0.11
     personalized
    -0.11
    eln
    -0.11
     Relatives
    -0.10
     femin
    -0.10
    JA
    -0.10
    POSITIVE LOGITS
     HD
    0.25
     crisp
    0.24
     resolution
    0.24
     visually
    0.23
     resolutions
    0.21
     visuals
    0.21
    HD
    0.20
     clarity
    0.19
     viewing
    0.19
     Resolution
    0.19
    Activations Density 0.133%

    No Known Activations