© 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. 33158
    Prev
    Next
    INDEX
    Explanations

    art and creative works

    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
     sne
    -0.11
     competitions
    -0.10
    Extras
    -0.10
    rimon
    -0.09
    amer
    -0.09
     propos
    -0.09
    optic
    -0.09
    amas
    -0.09
    rek
    -0.09
    anim
    -0.09
    POSITIVE LOGITS
     masterpiece
    0.25
     canvas
    0.21
     sym
    0.19
     sculpt
    0.19
     Symphony
    0.19
     Canvas
    0.17
     cresc
    0.17
    canvas
    0.17
     canv
    0.17
     orchest
    0.16
    Activations Density 0.049%

    No Known Activations