© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18400
    Prev
    Next
    INDEX
    Explanations

    affairs and illicit relationships

    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
    alic
    -0.09
    åĮ¾
    -0.09
    æºī
    -0.09
    çł´
    -0.09
     ASC
    -0.08
    ä¸įåĬ¨
    -0.08
    åĬ¬
    -0.08
    åİ©
    -0.08
    çĽijæĬ¤
    -0.08
    åľ°çIJĨ
    -0.08
    POSITIVE LOGITS
    åĩºè½¨
    0.15
    å¬ĸ
    0.11
    红éħĴ
    0.10
    é²ľèī³
    0.10
    æ³¥
    0.10
    æļ§æĺ§
    0.10
    é²ľæ´»
    0.10
    éļIJ身
    0.10
    缩
    0.10
    å§ĺ
    0.10
    Activations Density 0.047%

    No Known Activations