© 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. 92065
    Prev
    Next
    INDEX
    Explanations

    naked or nude followed by visual content

    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
    item
    -0.07
     bark
    -0.07
    ikal
    -0.07
    usk
    -0.07
     internally
    -0.07
     fed
    -0.07
    topl
    -0.07
    borg
    -0.07
     coached
    -0.07
    ipl
    -0.07
    POSITIVE LOGITS
     photos
    0.15
     Photos
    0.14
     mole
    0.13
     pictures
    0.13
     selfies
    0.13
     pics
    0.13
     Pics
    0.13
     bodies
    0.13
     Bodies
    0.12
    truth
    0.12
    Activations Density 0.004%

    No Known Activations