© 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. 51521
    Prev
    Next
    INDEX
    Explanations

    do / does

    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
    çĻ»ä¸Ĭ
    -0.10
    æĶ¾åģĩ
    -0.09
     Brace
    -0.09
     fred
    -0.09
    表达äºĨ
    -0.09
     Ingram
    -0.09
    å½ĵåģļ
    -0.09
     Sears
    -0.09
    /board
    -0.09
    å½ĵä½ľ
    -0.09
    POSITIVE LOGITS
    éĿĻéĿĻ
    0.09
    èł¢
    0.09
    ãģŀ
    0.09
    åįķä¸Ģ
    0.08
    yd
    0.08
    ãģĭãģijãĤĭ
    0.08
    èļķ
    0.08
    éĿĻéĿĻåľ°
    0.08
    hr
    0.08
    ç»ĻæĪij
    0.08
    Activations Density 0.043%

    No Known Activations