© 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. 37321
    Prev
    Next
    INDEX
    Explanations

    someone says

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.10
    å¾ĹäºĨ
    -0.10
    alert
    -0.09
    è¦ģä¹Ī
    -0.09
    åıĪ被
    -0.08
    оваÑĢ
    -0.08
     negoci
    -0.08
    mem
    -0.08
    被
    -0.08
    ä¸ĭåİ»
    -0.08
    POSITIVE LOGITS
    声称
    0.12
    åħ¬åijĬ称
    0.11
    浸
    0.11
    宣称
    0.10
    itet
    0.10
    AMPL
    0.09
    è¿ľæĸ¹
    0.09
    èĩªè±ª
    0.09
    æį®ä»ĭç»į
    0.08
    å¾ľ
    0.08
    Activations Density 0.071%

    No Known Activations