© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5837
    Prev
    Next
    INDEX
    Explanations

    sexual attractivity, quality, and dysfunction

    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
     sectional
    -0.09
     Selenium
    -0.09
     electoral
    -0.08
     sexuality
    -0.08
     security
    -0.08
     sweetness
    -0.08
    arine
    -0.08
     Sutton
    -0.08
     scheduled
    -0.08
     shoe
    -0.08
    POSITIVE LOGITS
     intercourse
    0.11
     prowess
    0.09
     misdemean
    0.09
    ilst
    0.09
     grat
    0.09
    pch
    0.09
     pans
    0.08
    .Manifest
    0.08
     maturity
    0.08
     ylabel
    0.08
    Activations Density 0.097%

    No Known Activations