© 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. 20696
    Prev
    Next
    INDEX
    Explanations

    insertion into cavities

    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
    æĹ©çĤ¹
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    æĥ³çŁ¥éģĵ
    -0.09
    æĿ²
    -0.08
    å¸ĺ
    -0.08
    ä¸Ģåı£æ°Ķ
    -0.08
    éĢı
    -0.08
    çĴ©
    -0.08
    çľ·
    -0.08
    伤å¿ĥ
    -0.08
    POSITIVE LOGITS
    åĺ»åĺ»
    0.09
    åĢ¡å¯¼
    0.09
    è¿Ľåĩº
    0.09
    弩
    0.09
    -clear
    0.08
    ç¥ĵ
    0.08
    ouser
    0.08
    otton
    0.08
     Luo
    0.08
    åĢ¡è®®
    0.08
    Activations Density 0.178%

    No Known Activations