© 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. 36907
    Prev
    Next
    INDEX
    Explanations

    IT administration and training

    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
    /GPL
    -0.09
    è§ħ
    -0.08
    reinterpret
    -0.08
    azor
    -0.08
    redit
    -0.08
    éĩįæĸ°
    -0.08
    æݨ
    -0.08
    éħįå¥Ĺ
    -0.08
    _ped
    -0.08
    æ¸łéģĵ
    -0.08
    POSITIVE LOGITS
    è¿IJç»´
    0.12
    ç»ıéªĮ
    0.10
    å®ŀè·µç»ıéªĮ
    0.09
    èģĮä¸ļæĬĢæľ¯
    0.09
     technician
    0.09
    ä¸ĵä¸ļæĬĢæľ¯
    0.09
     Disposable
    0.09
    VEST
    0.09
    uple
    0.09
     админиÑģÑĤ
    0.09
    Activations Density 0.165%

    No Known Activations