© 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. 10233
    Prev
    Next
    INDEX
    Explanations

    good descriptions

    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
    è¿«
    -0.08
    éĩı
    -0.08
    lan
    -0.08
    裾
    -0.08
     kol
    -0.08
     Witt
    -0.08
    å¾®éĩıåħĥç´ł
    -0.08
    tam
    -0.08
    æĦĪ
    -0.08
    å¾Īæľī
    -0.07
    POSITIVE LOGITS
    æĮĩå¼ķ
    0.10
    缸å¤Ħ
    0.10
    å¡ŀ
    0.09
    åģļ梦
    0.09
    é¸
    0.09
    æ¦ľ
    0.09
    åľ¨ç¾İåĽ½
    0.09
    rgan
    0.09
    è¿Ļå¼ł
    0.09
    绩
    0.09
    Activations Density 0.064%

    No Known Activations