© 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. 8916
    Prev
    Next
    INDEX
    Explanations

    this concept

    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
    IBC
    -0.10
    ady
    -0.08
    æĸ°åĬł
    -0.08
    æŀ¶
    -0.08
     اÙĦتاب
    -0.08
    arat
    -0.08
    çĺ¾
    -0.08
    ï¬Ħ
    -0.08
    inia
    -0.08
    æ¬²æľĽ
    -0.08
    POSITIVE LOGITS
     ones
    0.15
    ones
    0.11
    ç¾İ人
    0.10
    åIJĮè¡Į
    0.09
    ä¸Ģ个æĺ¯
    0.09
    åģķ
    0.09
    è¿Ļ对
    0.09
    çĶ©
    0.09
    ä¸Ģå°ģ
    0.08
    èĩªè§ī
    0.08
    Activations Density 0.071%

    No Known Activations