© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51794
    Prev
    Next
    INDEX
    Explanations

    Copyright notice

    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
     enr
    -0.10
    蹩
    -0.10
    绣çŃ¹æİ¨è¿Ľ
    -0.09
    wish
    -0.09
    utta
    -0.09
     Clem
    -0.09
    èī²æ³½
    -0.08
    åĪĨ管
    -0.08
    åįĬ天
    -0.08
    ä¸įé«ĺ
    -0.08
    POSITIVE LOGITS
    书æ³ķ
    0.09
    å®Ī
    0.09
    ogra
    0.09
    çļ®éĿ©
    0.09
    åĬŁå¤«
    0.08
    å°±æĺ¯è¿Ļæł·
    0.08
    inst
    0.08
    ä¹Ĺ
    0.08
    åħ±åĴĮåĽ½
    0.08
    奴éļ¶
    0.08
    Activations Density 0.142%

    No Known Activations