© 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. 9473
    Prev
    Next
    INDEX
    Explanations

    software features

    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
    ewe
    -0.09
    edm
    -0.09
    æ¼Ĩ
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
    åį°åĪ·
    -0.09
    æĮªå¨ģ
    -0.08
    éĢłçº¸
    -0.08
    çĬĬ
    -0.08
    _CORE
    -0.08
    _core
    -0.08
    POSITIVE LOGITS
    踪
    0.09
     bump
    0.09
    ç¿ĺ
    0.09
    alia
    0.08
    _utilities
    0.08
    Anywhere
    0.08
    æ´İ
    0.08
    å¤ĩ
    0.07
    æŀĦ
    0.07
    SED
    0.07
    Activations Density 0.394%

    No Known Activations