© 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. 115609
    Prev
    Next
    INDEX
    Explanations

    woman might say yes

    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
    hir
    -0.10
     оп
    -0.09
     inert
    -0.09
     husband
    -0.09
     cute
    -0.09
     girls
    -0.08
     externally
    -0.08
    neg
    -0.08
     Girls
    -0.08
    ital
    -0.08
    POSITIVE LOGITS
     Accepted
    0.13
     entr
    0.12
     accepted
    0.11
     Trap
    0.11
     ACCEPT
    0.11
     vests
    0.11
    nos
    0.11
     Reject
    0.11
     Reward
    0.10
    Trap
    0.10
    Activations Density 0.028%

    No Known Activations