© 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. 8642
    Prev
    Next
    INDEX
    Explanations

    double-blind studies

    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
    ensen
    -0.10
    滿
    -0.10
    Ñĩин
    -0.09
    åľ°äº§
    -0.09
     Innoc
    -0.09
    满
    -0.08
    _ACT
    -0.08
    èĩ»
    -0.08
    çĭ¬å®¶
    -0.08
     Hess
    -0.08
    POSITIVE LOGITS
    _refl
    0.09
    ä¸įæ¸ħ
    0.08
    ìĬ¤íģ¬
    0.08
    à¹īà¸ĩ
    0.08
    æİ¥çĿĢ
    0.08
    æĻ¦
    0.08
    è¿Ļæł·æīįèĥ½
    0.08
    çĽ²
    0.08
    ä¸Ģ缴åĪ°
    0.08
    CADE
    0.08
    Activations Density 0.104%

    No Known Activations