© 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. 7901
    Prev
    Next
    INDEX
    Explanations

    time duration phrases

    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
    æ¿Ĵ
    -0.10
    æķij人
    -0.09
    çIJ´
    -0.09
    é¾¢
    -0.09
    ä¸ĭæ²ī
    -0.09
    åīį段æŶéĹ´
    -0.09
    hör
    -0.09
    æ¯ı次éĥ½
    -0.08
    ä¸įæŃ»
    -0.08
    èķĬ
    -0.08
    POSITIVE LOGITS
    çŀ¬éĹ´
    0.18
    ä¸Ģçŀ¬éĹ´
    0.16
    çŀ¬
    0.13
    çľ¨çľ¼
    0.12
    ç§ĴéĴŁ
    0.12
    çŁŃçŁŃ
    0.12
    Instant
    0.11
    é¡·
    0.11
    ä¸Ģä¸ĭåŃIJå°±
    0.11
    éľİ
    0.11
    Activations Density 0.058%

    No Known Activations