© 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. 19345
    Prev
    Next
    INDEX
    Explanations

    let's get some

    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
    èIJ½åħ¥
    -0.10
    ä¸ĵåĮº
    -0.09
    nis
    -0.09
    å²Ļ
    -0.09
    è¿ĺ好
    -0.09
    åĨĴçĿĢ
    -0.09
    çļĦä¸Ģéĥ¨åĪĨ
    -0.09
    éļ¶
    -0.09
    åĴ£
    -0.08
    å¾Īå¿«
    -0.08
    POSITIVE LOGITS
    elder
    0.10
    çľĭçľĭ
    0.09
    @qq
    0.09
     إذ
    0.09
     Lonely
    0.09
    ä¸įè¦ģ
    0.09
     lonely
    0.09
    è¯ķè¯ķ
    0.09
    ạt
    0.08
    -cond
    0.08
    Activations Density 0.023%

    No Known Activations