© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9650
    Prev
    Next
    INDEX
    Explanations

    office or chapter

    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
    åĩºçİ°åľ¨
    -0.10
    ä»İå°ı
    -0.08
    éĺ´éĺ³
    -0.08
    éĢļå¾Ģ
    -0.08
    æ³ķè§Ħ
    -0.08
    ç»´å¥ĩ
    -0.08
    éĺ´
    -0.08
    åĪĩæĸŃ
    -0.08
    estion
    -0.08
    åĩºå¢ĥ
    -0.07
    POSITIVE LOGITS
    /world
    0.10
    inka
    0.09
    æľĪèĸª
    0.09
    æĹĭ
    0.09
    åĺĺ
    0.09
    ffects
    0.08
     Closet
    0.08
    åħ»èĢģéĩij
    0.08
    ÑĪка
    0.08
    è¾Ľ
    0.08
    Activations Density 0.098%

    No Known Activations