© 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. 37182
    Prev
    Next
    INDEX
    Explanations

    get help or assistance

    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
     rents
    -0.10
    ç¼Ģ
    -0.09
     Pou
    -0.09
    åĽ´
    -0.08
    çĻ¾äº¿
    -0.08
    æĩĶ
    -0.08
     flex
    -0.08
    uzzi
    -0.08
    æ°ijæĹı
    -0.08
    (TEXT
    -0.08
    POSITIVE LOGITS
     sought
    0.12
    寻æ±Ĥ
    0.12
     seek
    0.11
     liá»ĩu
    0.11
    Seek
    0.10
    éĩįå·¥
    0.10
    seek
    0.10
    wers
    0.10
    .seek
    0.10
    ä»ĸæĽ¾
    0.10
    Activations Density 0.047%

    No Known Activations