© 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. 53344
    Prev
    Next
    INDEX
    Explanations

    suspension pending appeal

    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
    æĶ¾å¼ĥäºĨ
    -0.11
    åĽŀæĶ¶
    -0.10
    é¢Ĩ
    -0.10
    åī©
    -0.10
    æ¹Ķ
    -0.09
    æ°¸ä¸į
    -0.08
    çĹ¼
    -0.08
    æĶ¾å¼ĥ
    -0.08
    ipe
    -0.08
    æĶ¶åĽŀ
    -0.08
    POSITIVE LOGITS
    æļĤæŶ
    0.18
    æļĤ
    0.16
    æľŁéĹ´
    0.15
    åħĪè¡Į
    0.15
     interim
    0.15
    缴åĪ°
    0.15
    è¿Ļ段æŶéĹ´
    0.14
    æļ«
    0.14
    until
    0.13
     until
    0.13
    Activations Density 0.197%

    No Known Activations