© 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. 52008
    Prev
    Next
    INDEX
    Explanations

    add or implement functionality

    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
    çĥŃæĴŃ
    -0.09
    çĭĤ欢
    -0.09
    ohn
    -0.08
     Aud
    -0.08
    çIJ°
    -0.08
    enson
    -0.08
    inke
    -0.08
    æķ´é¡¿
    -0.08
    è£ħå¤ĩåĪ¶éĢł
    -0.08
    ãģ©ãģ®
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Īåģļ
    0.14
    è¿Ļç§įæĥħåĨµ
    0.13
    è¿Ļæł·åģļ
    0.12
    è¿Ļç§įæĸ¹æ³ķ
    0.12
    è¿Ļç§į
    0.11
    æŃ¤ä¸¾
    0.10
    è®©ä½ł
    0.10
     ÑĤакого
    0.10
    è¿Ļç§įäºĭæĥħ
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.09
    Activations Density 0.592%

    No Known Activations