© 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. 52081
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
    æĪªèĩ³
    -0.08
    arnation
    -0.08
    ä½Ľæ³ķ
    -0.07
    æĪªæŃ¢
    -0.07
    fest
    -0.07
    (tc
    -0.07
    缴èĩ³
    -0.07
    çĬ¯
    -0.07
    clus
    -0.07
    .cfg
    -0.07
    POSITIVE LOGITS
    大éĻĨ
    0.11
    äºĨä¸įå°ij
    0.10
    çĽĬ
    0.10
    ÄŁu
    0.09
    è¿İæĿ¥äºĨ
    0.09
    çĶŃ
    0.09
    åģ·åģ·
    0.09
    ogenerated
    0.09
    éĩijæ²Ļ
    0.09
    åĶ¬
    0.09
    Activations Density 0.056%

    No Known Activations