© 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. 36726
    Prev
    Next
    INDEX
    Explanations

    .port= logging.level.org Package logrus

    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
    æĺİæĻ°
    -0.11
    çĬĬ
    -0.10
    åıĹçĽĬ
    -0.10
    å®īåħ¨ä¿Ŀéļľ
    -0.10
    社ä¼ļä¿Ŀéļľ
    -0.09
     pylint
    -0.09
    åĿļå®ŀçļĦ
    -0.09
    ÅŁt
    -0.09
    å¹³æ°ij
    -0.09
    èĩ¾
    -0.09
    POSITIVE LOGITS
    eler
    0.08
    inn
    0.08
    lesh
    0.08
    ลา
    0.08
     tier
    0.08
     pil
    0.08
     excer
    0.08
    tier
    0.07
    象
    0.07
    mouseover
    0.07
    Activations Density 0.011%

    No Known Activations