© 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. 20881
    Prev
    Next
    INDEX
    Explanations

    within minutes or hours

    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
    èĬ±äºĨ
    -0.11
    é£İå°ļ
    -0.10
    åĵģä½į
    -0.10
    æ®Ħ
    -0.09
    çİ°å·²
    -0.09
    æī§æ³ķ人åijĺ
    -0.09
    éģ¥è¿ľ
    -0.09
    è¿ľæĸ¹
    -0.09
    æł·åŃIJ
    -0.09
    åıªä¸º
    -0.09
    POSITIVE LOGITS
    åī¥
    0.09
    ington
    0.09
    GMT
    0.09
    çıĢ
    0.09
    active
    0.08
    stud
    0.08
    cratch
    0.08
    .Support
    0.08
    æĦŁæŁĵ
    0.08
    _Char
    0.08
    Activations Density 0.018%

    No Known Activations