© 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. 20371
    Prev
    Next
    INDEX
    Explanations

    German place names suffixes

    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
    Ñĩик
    -0.10
    clip
    -0.08
    à¦ĵ
    -0.08
    æĺ¨æĻļ
    -0.08
     forthcoming
    -0.08
    rint
    -0.08
    بد
    -0.08
    åīįãģ«
    -0.08
    ANY
    -0.08
    楼
    -0.08
    POSITIVE LOGITS
    ness
    0.25
    ãģªãĤĤãģ®
    0.19
    ãģª
    0.19
    NESS
    0.17
    ä¸İåIJ¦
    0.16
    ly
    0.16
    ä¹ĭå¤Ħ
    0.15
    ities
    0.14
    à¹Ĩ
    0.14
    ãģªãģĬ
    0.14
    Activations Density 0.227%

    No Known Activations