© 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. 19651
    Prev
    Next
    INDEX
    Explanations

    building wealth and savings

    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
    é²ģèĥ½
    -0.09
    åIJĪä½ľåħ±èµ¢
    -0.09
     squeeze
    -0.09
    SDK
    -0.09
    åĪĢ
    -0.08
    odo
    -0.08
    åĩºåĽ½
    -0.08
    è¿İåIJĪ
    -0.08
    squeeze
    -0.08
    ä¹ĭå¤ĸ
    -0.08
    POSITIVE LOGITS
    .dispatch
    0.11
    rame
    0.09
    ä½ĺ
    0.09
    бав
    0.09
    è¾ŀ
    0.09
    lex
    0.09
    èµ·çłģ
    0.08
    éĽ¹
    0.08
    æ²¥
    0.08
    å©Ĩå©Ĩ
    0.08
    Activations Density 0.080%

    No Known Activations