© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    jeopardize or compromise

    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
    виÑĤ
    -0.10
    èĻ¹
    -0.10
    èħ»
    -0.09
    mun
    -0.08
    æѧè§Ĩ
    -0.08
    å²ij
    -0.08
    åĬ«
    -0.08
    isma
    -0.08
    头ä¸Ĭ
    -0.08
    åģıå·®
    -0.08
    POSITIVE LOGITS
    åĽ½å®¶å®īåħ¨
    0.11
    пл
    0.09
    å´Ħ
    0.09
    éķĸ
    0.09
     lÃłnh
    0.09
    社ä¼ļ稳å®ļ
    0.09
    .currentState
    0.08
    æī¾ä¸ª
    0.08
    쿨
    0.08
    个人
    0.08
    Activations Density 0.010%

    No Known Activations