© 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. 36430
    Prev
    Next
    INDEX
    Explanations

    exploring new techniques

    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
    eri
    -0.11
    æĬĬä½ł
    -0.10
    æıIJåĩºçļĦ
    -0.10
    onom
    -0.09
    èĮĤ
    -0.09
    浪
    -0.09
    åĶł
    -0.09
    æīĵ交éģĵ
    -0.08
    åģļçĶŁæĦı
    -0.08
    建çŃij设计
    -0.08
    POSITIVE LOGITS
    è¯ķçĤ¹
    0.15
     pione
    0.13
    è¯ķçĤ¹å·¥ä½ľ
    0.12
    æݨ广
    0.11
    è¿Ļ项
    0.11
    æѤäºĭ
    0.10
    è§Ħ模
    0.10
     reap
    0.09
    è¯ķè¡Į
    0.09
    è¦ı模
    0.09
    Activations Density 0.379%

    No Known Activations