© 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. 62382
    Prev
    Next
    INDEX
    Explanations

    examining relationships or outcomes of actions

    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
    åłħæĮģ
    -0.10
    ãĥªãĤ¢ãĥ«
    -0.09
    æķ£å¸ĥ
    -0.09
    åĿļæĮģ
    -0.09
    å®ŀåľ°
    -0.09
    åģ¥åº·åıijå±ķ
    -0.09
    羣å®ŀçļĦ
    -0.09
    èĩªæĦ¿
    -0.09
    åĢ¼å¾Ĺåħ³æ³¨
    -0.08
    çİ°å®ŀçĶŁæ´»
    -0.08
    POSITIVE LOGITS
    表éĿ¢ä¸Ĭ
    0.12
    ä¸ĢæŶ
    0.11
    åĻ±
    0.10
    ä¹ĭæīĢ
    0.10
    表éĿ¢
    0.10
    æŁIJä¸Ģ
    0.09
    åĭī强
    0.09
    ä¸Ģåij³
    0.09
     ÐĶе
    0.09
    ä»ħä»ħæĺ¯
    0.08
    Activations Density 0.280%

    No Known Activations