© 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. 38102
    Prev
    Next
    INDEX
    Explanations

    these + noun

    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
    åŃ¦å®¶
    -0.10
    èĥ¸åīį
    -0.10
    _STAR
    -0.09
    çݺ
    -0.09
    纺
    -0.09
    è¿ĻåĿĹ
    -0.09
    è´Łè´£åIJĮå¿Ĺ
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    è¿ĻæĿ¡
    -0.08
    è°
    -0.08
    POSITIVE LOGITS
     such
    0.20
    è¿Ļæł·çļĦ
    0.20
    æѤ类
    0.18
     Such
    0.18
    Such
    0.18
    such
    0.16
     ÑĤакой
    0.16
     ÑĤакого
    0.15
    ãĤĪãģĨãģª
    0.14
    éĤ£æł·çļĦ
    0.14
    Activations Density 0.144%

    No Known Activations