© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23624
    Prev
    Next
    INDEX
    Explanations

    questions and statements

    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
    ä¹ĭ家
    -0.08
    çĽ¸äº²
    -0.08
    ä¸įåIJĮæĦı
    -0.08
    ован
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    å½ĸ
    -0.08
    åĪ©
    -0.08
    ENTE
    -0.07
    æ²Ĩ
    -0.07
     Trit
    -0.07
    POSITIVE LOGITS
    è¿Ļ个éĹ®é¢ĺ
    0.21
    è¿ĻäºĽéĹ®é¢ĺ
    0.14
    çļĦçŃĶæ¡Ī
    0.14
    çŃīéĹ®é¢ĺ
    0.13
    çļĦåĽŀçŃĶ
    0.13
     question
    0.13
     вопÑĢоÑģ
    0.13
    询éĹ®
    0.12
    éĹ®ä»ĸ
    0.12
    éĹ®
    0.12
    Activations Density 0.130%

    No Known Activations