© 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. 29058
    Prev
    Next
    INDEX
    Explanations

    testosterone levels

    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
     Dawn
    -0.08
    ist
    -0.08
     ante
    -0.08
     dip
    -0.07
    asia
    -0.07
     adrenaline
    -0.07
    opot
    -0.07
     anymore
    -0.07
     Haley
    -0.07
    istani
    -0.07
    POSITIVE LOGITS
    elle
    0.11
    ously
    0.11
    udy
    0.11
    ãĤ£
    0.10
    Levels
    0.10
     Lehr
    0.10
    REAM
    0.10
    erties
    0.10
     Levels
    0.10
     komen
    0.10
    Activations Density 0.002%

    No Known Activations