© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36485
    Prev
    Next
    INDEX
    Explanations

    innocence and purity

    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
    INLINE
    -0.08
    ä½İè°ĥ
    -0.08
    æīĴ
    -0.08
    ãĥ½
    -0.08
    -muted
    -0.08
    invisible
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
     invis
    -0.08
    é¼ĵèĪŀ
    -0.08
    èĤĺ
    -0.08
    POSITIVE LOGITS
     innocence
    0.15
     innocent
    0.13
    æĹłè¾ľ
    0.12
    æĹłçŁ¥
    0.11
    ä¸įæĩĤ
    0.11
     Innoc
    0.11
    æĹłå¿§
    0.10
    å¤©çľŁ
    0.10
     Weiner
    0.10
    åįķ纯
    0.10
    Activations Density 0.018%

    No Known Activations