© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51990
    Prev
    Next
    INDEX
    Explanations

    beginning or ending

    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
    tape
    -0.10
    \\/
    -0.10
    è°¯
    -0.09
    å½ĵæŶçļĦ
    -0.09
    丼
    -0.09
    èİī
    -0.09
    oha
    -0.08
    åıijè¾¾
    -0.08
    abad
    -0.08
    ä»
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁ
    0.17
    ç»ĵå°¾
    0.17
    æľĢåIJİ
    0.14
    æľĢå¾Į
    0.13
     koÅĦ
    0.13
     ending
    0.13
    çµIJæĿŁ
    0.13
    ç»ĵæĿŁäºĨ
    0.12
     cuá»iji
    0.12
    èµ·æŃ¥
    0.11
    Activations Density 0.060%

    No Known Activations