© 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. 9987
    Prev
    Next
    INDEX
    Explanations

    visitors login

    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
     ÑģÑĭ
    -0.09
    åıĤåĬłäºĨ
    -0.08
    éĨĴ
    -0.08
    åĩºåħ¥
    -0.08
    åı£å¾Ħ
    -0.08
    ä¾Ī
    -0.08
    éĢī
    -0.08
    jur
    -0.08
    åħ¥åľº
    -0.08
    æĺ¯ä¸Ģ件
    -0.08
    POSITIVE LOGITS
    çķĻä½ı
    0.11
    è§Ĥä¼Ĺ
    0.10
    宽带
    0.09
     extr
    0.09
    å½¼
    0.09
    éĺħ
    0.09
    è§ĨåIJ¬
    0.09
    OTOS
    0.09
    è§Ĩè§ī
    0.09
    ä¸įè§ģ
    0.08
    Activations Density 0.058%

    No Known Activations