© 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. 52908
    Prev
    Next
    INDEX
    Explanations

    bacterial pathogens

    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
    æĭīä¸ģ
    -0.09
    ç¾½æ¯Ľ
    -0.09
    Axes
    -0.09
    Ñĥж
    -0.08
    _AXIS
    -0.08
    éħ¹
    -0.08
    裼
    -0.08
    åĻ¨å®ĺ
    -0.08
    æĬĴ
    -0.08
    ollo
    -0.07
    POSITIVE LOGITS
    便æ°ij
    0.14
    å¢ŀ设
    0.13
    æĬķè¯ī
    0.13
    å·¡éĢ»
    0.13
    æĶ¹åĸĦ
    0.12
    åĢ¡å¯¼
    0.11
    åŁİ管
    0.10
    æķ´æ²»
    0.10
     enforcement
    0.10
    åħ¬åħ±äº¤éĢļ
    0.10
    Activations Density 0.111%

    No Known Activations