© 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. 17199
    Prev
    Next
    INDEX
    Explanations

    facing challenges

    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
    éģĵçIJĨ
    -0.08
    çİ«
    -0.08
     Wich
    -0.08
    åģİ
    -0.08
    éļ¶å±ŀ
    -0.08
    éģĽ
    -0.08
    åĪĨå·¥
    -0.08
    oad
    -0.08
     something
    -0.08
    åIJı
    -0.08
    POSITIVE LOGITS
    å¸ļ
    0.10
    åħ¨ä½ĵ
    0.10
    ä»»ä½ķä¸Ģ个
    0.10
    å¹´è½»
    0.09
    è¿Ļ对
    0.09
    åķ¼
    0.09
    çĽ¼
    0.09
    è¸Į
    0.09
    rzy
    0.09
    æĸ°çĶŁ
    0.08
    Activations Density 0.020%

    No Known Activations