© 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. 17499
    Prev
    Next
    INDEX
    Explanations

    endure harsh conditions

    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
    åĨĴçĿĢ
    -0.09
    -toggler
    -0.09
     Obt
    -0.09
    åıĸå¾Ĺ
    -0.09
    ä¸į足
    -0.09
    裾
    -0.09
    弦
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    åıĸå¾ĹäºĨ
    -0.08
    çļĦçŁ¥è¯Ĩ
    -0.08
    POSITIVE LOGITS
    èĭĽ
    0.10
    æĢİä¹ĪåĽŀäºĭ
    0.09
    æŀģé«ĺ
    0.08
    _TW
    0.08
    èĢĥæł¸
    0.08
    ä¸įå¿ĺ
    0.08
    ä¸įæĸŃæıIJåįĩ
    0.08
     ÑĢа
    0.08
    èĢĥè¯Ħ
    0.08
    phis
    0.08
    Activations Density 0.091%

    No Known Activations