© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21207
    Prev
    Next
    INDEX
    Explanations

    artists and bands

    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
     pops
    -0.09
    伦
    -0.09
    ä¸Ģæŀļ
    -0.08
    MMC
    -0.08
    edic
    -0.08
    æij©æīĺ
    -0.08
    ä¾į
    -0.08
    åıŁ
    -0.08
    屯
    -0.08
    lep
    -0.08
    POSITIVE LOGITS
    éĽ¾
    0.10
    å¯ĤéĿĻ
    0.09
    å¹½
    0.09
     whispered
    0.09
    æ³£
    0.09
    zac
    0.09
    åĩĦ
    0.09
    æĹłå£°
    0.08
    lust
    0.08
    éľ¾
    0.08
    Activations Density 0.080%

    No Known Activations