© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19117
    Prev
    Next
    INDEX
    Explanations

    help finding, shopping, writing, proving, getting

    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
    Negative Logits
    ogl
    -0.10
    ety
    -0.09
    æĦŁåºĶ
    -0.08
    èµĸ以çĶŁåŃĺ
    -0.08
    olan
    -0.08
    åĬŀäºĭ
    -0.08
    oras
    -0.08
    éŃĩ
    -0.08
    ç©·
    -0.08
    itori
    -0.08
    POSITIVE LOGITS
    å¼Ħ
    0.10
    หา
    0.09
    icare
    0.09
    åĻľ
    0.09
    éĻ¶
    0.09
    åĪĨå±Ģ
    0.09
    åľ¨è¿ĩ渡
    0.08
    åıijå±ķè§ĦåĪĴ
    0.08
    è´Łè´£ä»»
    0.08
    è¯ģåĪ¸æĬķèµĦ
    0.08
    Activations Density 0.044%

    No Known Activations