© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    financial aid and awards

    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
    å¤Ħå¤Ħ
    -0.10
    orry
    -0.09
    å¾ĹåĪ°äºĨ
    -0.09
    ÙħØŃ
    -0.08
    åħħæĸ¥
    -0.08
    åIJĦ个
    -0.08
    æݨåĩºçļĦ
    -0.08
    åĩłåįģå¹´
    -0.08
    便æ°ij
    -0.08
    acades
    -0.08
    POSITIVE LOGITS
    éĴµ
    0.10
    èµĦåĬ©
    0.09
     Marino
    0.09
    æĶ¯æĮģåĬĽåº¦
    0.09
    对ä¼ģä¸ļ
    0.09
    ç»ıè´¹
    0.09
    书éĻ¢
    0.09
    å¹´èĸª
    0.09
    çļĦèµĦéĩij
    0.08
    èģĺ请
    0.08
    Activations Density 0.045%

    No Known Activations