© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35699
    Prev
    Next
    INDEX
    Explanations

    death and destruction

    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
    éķ¿æķĪ
    -0.11
    รà¸Ńà¸ĩ
    -0.10
    (sem
    -0.10
    .sem
    -0.10
    对æĬĹ
    -0.09
    åģļå¾Ĺ
    -0.09
    beit
    -0.09
    å¹³æŶ
    -0.09
    æĥ°
    -0.09
    é²ij
    -0.09
    POSITIVE LOGITS
    æ®Ĵ
    0.13
    æĤ²åī§
    0.11
    åħ¨å®¶
    0.11
    æŃ»äºĨ
    0.11
    æ®Ĩ
    0.11
    å½ĵåľº
    0.10
    æ®ģ
    0.10
    éģĩéļ¾
    0.10
    æİīäºĨ
    0.10
    伤亡
    0.10
    Activations Density 0.093%

    No Known Activations