© 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. 52217
    Prev
    Next
    INDEX
    Explanations

    genre and genres

    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
    åİĿ
    -0.11
    çĮ¿
    -0.10
    èĭĩ
    -0.09
    วา
    -0.09
    å®īæ£Ģ
    -0.09
    ilit
    -0.09
    éĮ¯
    -0.09
     canv
    -0.08
    çľ¼ä¸Ń
    -0.08
    éģ´éĢī
    -0.08
    POSITIVE LOGITS
     genre
    0.19
     genres
    0.18
    é¢ĺæĿIJ
    0.16
     Genre
    0.15
    genre
    0.14
    genres
    0.14
    .genre
    0.13
    Genre
    0.13
    ãĤ¸ãĥ£ãĥ³
    0.12
    ç±»åĪ«
    0.12
    Activations Density 0.109%

    No Known Activations