© 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. 36330
    Prev
    Next
    INDEX
    Explanations

    technical topics and examples

    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
    çŃīä¸Ģæī¹
    -0.09
    çľĭä»ĸ
    -0.09
    åIJĮæŶè¿ĺ
    -0.08
    åľ¨ä»ĸçļĦ
    -0.08
    åIJĮæĹ¶ä¹Ł
    -0.08
    åŃĺåľ¨ä¸Ģå®ļ
    -0.08
    æĺ¯ä»ĸ
    -0.08
    å´ĸ
    -0.08
    hir
    -0.08
    éĵ°
    -0.07
    POSITIVE LOGITS
    åŁł
    0.10
    ç£ħ
    0.10
    æĭ¥æĮ¤
    0.09
    åıŁ
    0.09
     alike
    0.09
    éĥ½ä¸įèĥ½
    0.08
    _BUSY
    0.08
    LEM
    0.08
     bush
    0.08
    Spoiler
    0.08
    Activations Density 0.791%

    No Known Activations