© 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. 62356
    Prev
    Next
    INDEX
    Explanations

    prevent issues

    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
    赦
    -0.09
    æ³ĵ
    -0.09
    è¦ģåĿļæĮģ
    -0.09
    åį¡å°Ķ
    -0.09
    upert
    -0.09
     Killer
    -0.08
    compass
    -0.08
    女çİĭ
    -0.08
     inability
    -0.08
    ä¸įå¿į
    -0.08
    POSITIVE LOGITS
    åĩºçİ°
    0.12
    æĤ²åī§
    0.12
     future
    0.11
    ä¸ĩä¸Ģ
    0.11
    gos
    0.10
    äºĨä¸Ģåľº
    0.10
    åľ¨æľªæĿ¥
    0.10
    åĩºçı¾
    0.09
    丢失
    0.09
     becoming
    0.09
    Activations Density 0.049%

    No Known Activations