© 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. 37474
    Prev
    Next
    INDEX
    Explanations

    compliance, license, copyright, documentation

    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
     ÑĢаÑģÑģмаÑĤ
    -0.15
     misunder
    -0.15
    åĽłåľ°åĪ¶
    -0.15
     иÑģполÑĮзова
    -0.14
    èIJ½åĪ°å®ŀ
    -0.14
    æĪĸå¤ļæĪĸ
    -0.13
    åijĻ
    -0.13
    èĦ±é¢ĸ
    -0.13
    ä¹łè¿ijå¹³æĢ»
    -0.13
    ä¸İæĹ¶ä¿±
    -0.13
    POSITIVE LOGITS
     [âĢ¦]↵↵
    0.17
    ÂŃing
    0.14
     \↵
    0.11
     ...↵↵
    0.11
    ÂŃt
    0.10
     ...\
    0.09
     [âĢ¦
    0.09
    č↵
    0.09
    Č
    0.09
    ÂŃs
    0.09
    Activations Density 1.334%

    No Known Activations