© 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. 36232
    Prev
    Next
    INDEX
    Explanations

    leading into, leading to, opens to, connects to, goes to

    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
    ahoo
    -0.09
    æĮĩæĮ¥
    -0.09
    羣çĪ±
    -0.09
    岸边
    -0.09
    ä¸Ģé¡¿
    -0.09
    ắc
    -0.09
    ä¼łéĢģ
    -0.08
    æĿ¥åĽŀ
    -0.08
    åij¤
    -0.08
    åIJĪ计
    -0.08
    POSITIVE LOGITS
    éĢļå¾Ģ
    0.15
    è¿Ľåħ¥
    0.09
    ubb
    0.09
    御
    0.09
     Kb
    0.09
    anas
    0.09
    缴æİ¥
    0.09
    éĢ²åħ¥
    0.08
    åĶ¯ä¸Ģ
    0.08
    åĶ¯ä¸ĢçļĦ
    0.08
    Activations Density 0.048%

    No Known Activations