© 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. 31787
    Prev
    Next
    INDEX
    Explanations

    said that

    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
    äºĭä¸ļ
    -0.10
    æĤĦçĦ¶
    -0.10
    鹧
    -0.09
    é¼ł
    -0.09
    æĸ°çļĦä¸Ģ
    -0.09
    ãģķãģ¦
    -0.09
     Recorded
    -0.09
    å´¤
    -0.09
    opro
    -0.09
    åīĥ
    -0.09
    POSITIVE LOGITS
    ç¡®
    0.11
    å½ĵæŶ
    0.10
    æĪijå½ĵæŶ
    0.10
    è§ģè¿ĩ
    0.09
    åİ»è¿ĩ
    0.09
    çķ¶æĻĤ
    0.09
    è·Łä½ł
    0.09
    確
    0.08
    æĽ¾
    0.08
    èį¤
    0.08
    Activations Density 0.049%

    No Known Activations