© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11812
    Prev
    Next
    INDEX
    Explanations

    inquiries and assistance

    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
    ä¸Ģ
    -0.08
    åIJĦæĸ¹
    -0.08
    çĻ¾å®¶
    -0.08
    çļĦä¸ĢéĿ¢
    -0.07
     tre
    -0.07
     gorge
    -0.07
    urses
    -0.07
     Paste
    -0.07
    _lhs
    -0.07
    对æĬĹ
    -0.07
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.12
    æīĵæī°
    0.11
    çļĦæĦŁåıĹ
    0.11
    åºĶåıĬæŶ
    0.11
    è¿ĺæĥ³
    0.11
    åģĮ
    0.11
    éĻĩ
    0.11
    请èģĶç³»
    0.11
    æĶ¹éĿ©åıijå±ķ
    0.10
    å¼Ģåıij建设
    0.10
    Activations Density 0.040%

    No Known Activations