© 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. 6394
    Prev
    Next
    INDEX
    Explanations

    image editing and manipulation

    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
     Thornton
    -0.09
     penetr
    -0.08
    /cop
    -0.08
     foll
    -0.08
    igits
    -0.08
     decoded
    -0.08
     endurance
    -0.08
     independ
    -0.08
     Slate
    -0.08
    tee
    -0.08
    POSITIVE LOGITS
     tricks
    0.24
     photoshop
    0.22
     clever
    0.22
     editing
    0.21
     Photoshop
    0.21
     lighting
    0.21
     illusion
    0.18
     manipulation
    0.18
     Tricks
    0.18
     Editing
    0.17
    Activations Density 0.130%

    No Known Activations