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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52085
    Prev
    Next
    INDEX
    Explanations

    section

    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
    oons
    -0.10
     %+
    -0.09
    asco
    -0.09
    æŀĿ
    -0.08
    é¨
    -0.08
    为ä¹ĭ
    -0.07
    è¶ħè¿ĩ
    -0.07
    usk
    -0.07
    åĪ°æľŁ
    -0.07
    æºIJ
    -0.07
    POSITIVE LOGITS
    è¯įæĿ¡
    0.11
    失è°ĥ
    0.11
     section
    0.10
     здеÑģÑĮ
    0.10
    åħ³äºİ
    0.10
    çĿģ
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    ä¼ļè§īå¾Ĺ
    0.10
    梦è§ģ
    0.09
    è¿ĻåĦ¿
    0.09
    Activations Density 0.150%

    No Known Activations