© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 412
    Prev
    Next
    INDEX
    Explanations

    packet-switch, cell-free, drinking water, email harvesting, radioiodine, hair treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    2
    -0.22
    æĽ´å¥½åľ°
    -0.22
    AA
    -0.21
    -0.21
    就已ç»ı
    -0.21
    6
    -0.20
    ns
    -0.20
    1
    -0.20
    xaa
    -0.20
     seria
    -0.20
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.33
    åıĭ们
    0.29
    æĬ¥åijĬæĺ¾ç¤º
    0.28
    è°ĥæŁ¥æĺ¾ç¤º
    0.28
    claimer
    0.28
    å¤Ħå¤Ħéķ¿
    0.26
    åįıä¼ļä¼ļéķ¿
    0.25
    éĹ®é¢ĺæĺ¯
    0.25
    æķ°æį®æĺ¾ç¤º
    0.25
    éĽĸ
    0.24
    Activations Density 0.336%

    No Known Activations