© 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. 8475
    Prev
    Next
    INDEX
    Explanations

    issues and topics

    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
    å°ıåºĹ
    -0.09
    æĥħåĨµä¸ĭ
    -0.09
    ader
    -0.09
    utations
    -0.09
     sez
    -0.09
     Mile
    -0.09
    anson
    -0.09
    å·§
    -0.08
    èĪĽ
    -0.08
    ëŁ¼
    -0.08
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.16
    è¿Ļ个éĹ®é¢ĺ
    0.14
     how
    0.14
     issues
    0.12
    è¿ĻäºĽéĹ®é¢ĺ
    0.12
    è¿Ļ件äºĭ
    0.12
    å¦Ĥä½ķåİ»
    0.12
    çŃīéĹ®é¢ĺ
    0.11
    çļĦè¯Ŀé¢ĺ
    0.11
     topics
    0.11
    Activations Density 0.143%

    No Known Activations