© 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. 36637
    Prev
    Next
    INDEX
    Explanations

    customers and clients

    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
    è´§æŀ¶
    -0.10
    åĶ§
    -0.09
     CONTRIBUTORS
    -0.09
    客人
    -0.09
    æ±°
    -0.09
     доволÑĮ
    -0.09
    ç°¸
    -0.08
    ç»ıèIJ¥èĢħ
    -0.08
    æĸ°äºº
    -0.08
    venues
    -0.08
    POSITIVE LOGITS
    è¾Ľ
    0.09
    彪
    0.08
    enn
    0.08
    空åĨĽ
    0.08
    å¿«
    0.08
    Signals
    0.08
    еннÑĥÑİ
    0.08
    åIJĮç±»
    0.08
    çķĭ
    0.08
    utt
    0.08
    Activations Density 0.021%

    No Known Activations