© 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. 50312
    Prev
    Next
    INDEX
    Explanations

    feminine body parts

    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
     penis
    -0.12
     pant
    -0.12
    arest
    -0.12
    paragus
    -0.11
     dangling
    -0.11
     verbosity
    -0.11
    -submit
    -0.11
     toes
    -0.11
     fart
    -0.11
     Stern
    -0.11
    POSITIVE LOGITS
     hands
    0.11
     valley
    0.09
     Soft
    0.09
     soft
    0.09
     palm
    0.08
     Hands
    0.08
     hand
    0.08
     feminine
    0.08
     adorable
    0.07
     Craft
    0.07
    Activations Density 0.024%

    No Known Activations