© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11843
    Prev
    Next
    INDEX
    Explanations

    hexadecimal and alphanumeric sequences

    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
    åĴĮå®ĮåĸĦ
    -0.08
    æĺŁçIJĥ
    -0.08
    izr
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
     sham
    -0.08
    æĬĬè¿Ļ个
    -0.08
    inator
    -0.07
    erk
    -0.07
    åľ¨ä¸Ģ
    -0.07
    è¿ĻäºĽéĥ½æĺ¯
    -0.07
    POSITIVE LOGITS
    æł¹æľ¬æ²¡æľī
    0.09
    hora
    0.09
    EntryPoint
    0.09
    ä½
    0.09
    /or
    0.09
    ÙĪØ·
    0.08
    磼
    0.08
    çĸĿ
    0.08
    å±ŀ
    0.08
    好ä¸į好
    0.08
    Activations Density 0.401%

    No Known Activations