© 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. 14279
    Prev
    Next
    INDEX
    Explanations

    girls gender groups

    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
    .ActionListener
    -0.10
    @RequestMapping
    -0.09
     floors
    -0.08
     phosph
    -0.08
    blas
    -0.08
     Gins
    -0.08
     entitlement
    -0.08
     UITableViewDataSource
    -0.07
    URA
    -0.07
     copper
    -0.07
    POSITIVE LOGITS
     adults
    0.12
    raq
    0.12
     +:+
    0.11
     nuts
    0.11
     guys
    0.11
     useEffect
    0.11
     Brotherhood
    0.10
     guy
    0.10
     boys
    0.10
    itant
    0.10
    Activations Density 0.457%

    No Known Activations