© 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. 26888
    Prev
    Next
    INDEX
    Explanations

    satan, devils, Michael, battle

    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
    鸿
    -0.09
    èĩªåѦ
    -0.09
    èµ°ä¸ĭåİ»
    -0.09
    åĴ«
    -0.09
    æķijæı´
    -0.09
    æ§Ľ
    -0.09
    åĢĴåľ¨
    -0.09
     Bender
    -0.09
    æĦŁè§¦
    -0.09
    æŃ£å¥½
    -0.09
    POSITIVE LOGITS
    éŃĶ鬼
    0.10
    æĶ»åĩ»
    0.09
    ä¸ĥæĺŁ
    0.08
    AGE
    0.08
    åł¡åŀĴ
    0.08
    ANTS
    0.08
    ç«ĭæ¡Ī
    0.08
    èĥ½åģļåĪ°
    0.08
    _ATTR
    0.08
    çł´æįŁ
    0.08
    Activations Density 0.045%

    No Known Activations