© 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. 22200
    Prev
    Next
    INDEX
    Explanations

    found three

    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°Ĩ
    -0.09
    éĩįéĩį
    -0.08
    æľ¬æĸĩ
    -0.08
    ãģįãģ£ãģ¨
    -0.08
    ä¸į足以
    -0.08
    女æĺŁ
    -0.08
    该å¦Ĥä½ķ
    -0.08
    éļ¾æĢª
    -0.08
    è¿Ļä¸ĢåĪ»
    -0.08
    otor
    -0.08
    POSITIVE LOGITS
     ìłĢíĿ¬
    0.11
    æĪij个人
    0.11
    æĪij认为
    0.10
    æĪijè§īå¾Ĺ
    0.10
    åľ¨æĪijçļĦ
    0.10
    对æĪijæĿ¥è¯´
    0.10
    è§īå¾Ĺå¾Ī
    0.10
    æĪijçļĦ
    0.10
     my
    0.10
     myself
    0.09
    Activations Density 0.051%

    No Known Activations