© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6807
    Prev
    Next
    INDEX
    Explanations

    detox, sleep, stimulating, natural

    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
    çĤ¸
    -0.10
    shima
    -0.09
    éªij
    -0.09
    FirstChild
    -0.09
    FS
    -0.09
    ä¿Ŀ管
    -0.08
     Shade
    -0.08
    å½Ģ
    -0.08
    äºĶåĽĽ
    -0.08
    getParameter
    -0.08
    POSITIVE LOGITS
    æİĴæ¯Ĵ
    0.09
    é«ĺ端
    0.09
    çĶ¬
    0.09
    åħ»çĶŁ
    0.09
     jet
    0.09
    ä½ĵè´´
    0.09
    è¯Ĭ
    0.08
    çŧ
    0.08
     horm
    0.08
    èĬ³é¦Ļ
    0.08
    Activations Density 0.044%

    No Known Activations