© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49588
    Prev
    Next
    INDEX
    Explanations

    all the

    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
    éĥ¨åĪĨåľ°åĮº
    -0.11
    ä¸Ģçīĩ
    -0.11
    çļĦä¸Ģ大
    -0.11
    æķ´ä½ĵ
    -0.10
    çļĦä¸Ģåijĺ
    -0.10
    çļĦä¸Ģ项
    -0.10
    åıijå±ķçļĦ
    -0.10
    çļĦä¸Ģç§į
    -0.10
    æĸ°ä¸Ģè½®
    -0.10
    ä¸Ģç±»
    -0.10
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.12
     sorts
    0.10
    åħ¶ä»ĸ人
    0.09
    æĿ±è¥¿
    0.09
    鼶ç¢İ
    0.09
    oted
    0.09
    åħ¶ä»ĸ
    0.08
    Ao
    0.08
    åľºåIJĪ
    0.08
     Stafford
    0.08
    Activations Density 0.070%

    No Known Activations