© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 58659
    Prev
    Next
    INDEX
    Explanations

    other than

    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¿Ļæĺ¯ä¸Ģç§į
    -0.10
    /thumb
    -0.09
    rok
    -0.09
    è¯Ŀ说
    -0.09
    æį§
    -0.09
     zwar
    -0.09
    åħ¨åľº
    -0.08
    çĶŁæĢģæĸĩæĺİ
    -0.08
    çĬģ
    -0.08
    责任å¿ĥ
    -0.08
    POSITIVE LOGITS
    æ¶Ŀ
    0.12
     mere
    0.10
    halb
    0.09
    çļĦåħ³æ³¨
    0.09
    ä»ħä»ħ
    0.09
     há»ģ
    0.09
    than
    0.09
    åĩºäºİ
    0.08
    è¡ĮæĶ¿å¤Ħç½ļ
    0.08
    让大家
    0.08
    Activations Density 0.025%

    No Known Activations