© 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. 19724
    Prev
    Next
    INDEX
    Explanations

    depending on/upon

    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
    otechn
    -0.09
    æĽ´å¤ļçļĦ
    -0.08
    æł¼å¤ĸ
    -0.08
    ÑħоÑĤ
    -0.08
    /dom
    -0.08
    andy
    -0.08
    éĵ¿
    -0.08
    å¤ĩ
    -0.08
    罩
    -0.08
    ä¿Ĺè¯Ŀ说
    -0.08
    POSITIVE LOGITS
     depending
    0.12
    depending
    0.12
     Depending
    0.12
    åıĸåĨ³äºİ
    0.11
    Depending
    0.11
    èĤ¤
    0.10
    åıĸåĨ³
    0.10
    æ°ĶåĢĻåıĺåĮĸ
    0.10
    åıijå±ķéĺ¶æ®µ
    0.09
    -sex
    0.09
    Activations Density 0.025%

    No Known Activations