© 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. 50754
    Prev
    Next
    INDEX
    Explanations

    open minds

    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
     Overs
    -0.09
    æıŃ
    -0.09
    åĩıè½»
    -0.09
    æ¼ı
    -0.09
    åij½ä¸Ń
    -0.09
    overe
    -0.08
    èĤĭ
    -0.08
     bÃło
    -0.08
    ÃľN
    -0.08
    fall
    -0.08
    POSITIVE LOGITS
    åĮħ容
    0.22
    宽容
    0.18
    å¼ĢæĶ¾
    0.18
    æݥ纳
    0.17
    容纳
    0.16
     openness
    0.16
    éĸĭæĶ¾
    0.16
    对å¤ĸå¼ĢæĶ¾
    0.15
    åħ¼å®¹
    0.13
    容å¿į
    0.13
    Activations Density 0.086%

    No Known Activations