© 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. 36444
    Prev
    Next
    INDEX
    Explanations

    papillomavirus genital cancer

    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
     pac
    -0.09
    åĵ²
    -0.09
    æĬ±
    -0.08
     DISCLAIMER
    -0.08
    å¢Ļå£ģ
    -0.08
    æħĪæĤ²
    -0.08
    æ³Ħ
    -0.08
    ocity
    -0.08
    _fill
    -0.08
     Fill
    -0.08
    POSITIVE LOGITS
    穹
    0.12
    åİļåİļ
    0.10
    èĭĵ
    0.10
    她们
    0.09
    éĺ´éģĵ
    0.09
    å¹´è½»
    0.09
    ulum
    0.09
    æ§İ
    0.09
    untu
    0.09
     Lanka
    0.09
    Activations Density 0.242%

    No Known Activations