© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7561
    Prev
    Next
    INDEX
    Explanations

    female anatomy and hygiene

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    opa
    -0.10
    åĪĨæķ£
    -0.09
    被åĬ¨
    -0.09
    èĻº
    -0.09
    è¨ĵ
    -0.09
    è¢ĸ
    -0.09
    oplan
    -0.08
    osci
    -0.08
    glass
    -0.08
    çľ¼éķľ
    -0.08
    POSITIVE LOGITS
    è£Ĩ
    0.10
     exped
    0.09
    ä¾Ľåħ»
    0.09
    å°ıé¢Ŀ
    0.08
    èįī
    0.08
    éĺ´éģĵ
    0.08
    æѦè£ħ
    0.08
    èŀ¨
    0.08
    å°ıå·§
    0.08
    åĨħè¡£
    0.08
    Activations Density 0.226%

    No Known Activations