© 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. 8998
    Prev
    Next
    INDEX
    Explanations

    comment

    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
    ç½ijé¦ĸ页
    -0.09
    ’il
    -0.09
    æ±°
    -0.08
    ree
    -0.08
    æħ§
    -0.08
    'il
    -0.08
    midi
    -0.07
    ine
    -0.07
    _ij
    -0.07
     parts
    -0.07
    POSITIVE LOGITS
    endi
    0.09
    æĪ¾
    0.09
    OUS
    0.09
    æĪij们认为
    0.08
    Owned
    0.08
    idge
    0.08
    è´¸
    0.08
    ä¼ļ导èĩ´
    0.08
    éĢIJ
    0.08
    æĹłæĦı
    0.08
    Activations Density 0.155%

    No Known Activations