© 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. 8613
    Prev
    Next
    INDEX
    Explanations

    numbers and former

    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
    åĬª
    -0.09
    avit
    -0.08
     hete
    -0.08
    åijIJ
    -0.08
    quot
    -0.08
    opyright
    -0.08
    cly
    -0.08
    æ³½
    -0.08
    oyo
    -0.08
    ex
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个æĺ¯
    0.14
    åīįèĢħ
    0.14
    å®ĥ们
    0.12
    åIJİèĢħ
    0.12
    éĤ£è¾¹
    0.12
    ones
    0.12
     ÙħÙĨÙĩÙħ
    0.11
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.11
    åħ¶ä¸Ńä¸Ģ个
    0.11
    ãģªãĤĤãģ®
    0.11
    Activations Density 0.269%

    No Known Activations