© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111547
    Prev
    Next
    INDEX
    Explanations

    naked or nude

    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
    Negative Logits
    etch
    -0.09
     voluntarily
    -0.09
    usc
    -0.08
     Diy
    -0.08
    ario
    -0.08
     highlight
    -0.08
    arios
    -0.07
    cast
    -0.07
    -only
    -0.07
    alar
    -0.07
    POSITIVE LOGITS
    -eye
    0.13
     mole
    0.13
     Cul
    0.11
    ysi
    0.11
     Naked
    0.10
     Sext
    0.10
     aggression
    0.10
    nes
    0.10
    _fw
    0.09
     unarmed
    0.09
    Activations Density 0.028%

    No Known Activations