© 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. 20639
    Prev
    Next
    INDEX
    Explanations

    parole hearing or practices

    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
    æ·¡
    -0.10
    åIJĪä¸Ģ
    -0.09
    èĵ¦
    -0.09
    cott
    -0.09
    èħ»
    -0.08
    bulk
    -0.08
     phúc
    -0.08
     veg
    -0.08
    pha
    -0.08
    hey
    -0.08
    POSITIVE LOGITS
     Ingram
    0.10
    à¸Ļาม
    0.09
    å¨ĥ
    0.09
    تج
    0.09
    åĩłå®¶
    0.09
    ila
    0.09
    _Str
    0.08
    ä¸ĢæĬĬ
    0.08
    çĭ°
    0.08
    èĩ³ä»Ĭ
    0.08
    Activations Density 0.001%

    No Known Activations