© 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. 7444
    Prev
    Next
    INDEX
    Explanations

    take a, proceed through

    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
    èµĭäºĪ
    -0.10
    ubs
    -0.09
    賦
    -0.09
    èµĭ
    -0.09
    çĹħ人
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.09
    MESS
    -0.09
    èĢĥéªĮ
    -0.09
    åĶ®
    -0.09
    éĻªä¼´
    -0.09
    POSITIVE LOGITS
    åıĪ被
    0.14
    被
    0.14
    å¾ĹåĪ°
    0.13
    éĥ½è¢«
    0.12
    æİ¥åıĹäºĨ
    0.12
    æİ¥åıĹ
    0.11
    è®¤çľŁåŃ¦ä¹ł
    0.11
     receives
    0.11
    å¾ĹåĪ°æľīæķĪ
    0.11
     receive
    0.11
    Activations Density 0.453%

    No Known Activations