© 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. 20353
    Prev
    Next
    INDEX
    Explanations

    use of cookies and policy

    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
    ç¾Ĭ
    -0.08
    离
    -0.08
    æīĢå±ŀ
    -0.08
    зав
    -0.08
     Provid
    -0.07
    adoo
    -0.07
    ApiResponse
    -0.07
     PS
    -0.07
    åīįéĶĭ
    -0.07
    æĪªåĽ¾
    -0.07
    POSITIVE LOGITS
    ä¸Ģ家
    0.11
    eks
    0.10
    æĺ¯ä¸Ģ家
    0.10
    åľĥ
    0.10
    ãĤ¯ãĥ©ãĥĸ
    0.10
    iji
    0.10
     nouve
    0.10
    纳
    0.09
    åIJ¸çº³
    0.09
    管çIJĨåĴĮ
    0.09
    Activations Density 0.026%

    No Known Activations