© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3236
    Prev
    Next
    INDEX
    Explanations

    CERTIORARI TO

    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
    Negative Logits
    ixo
    -0.25
    è¶Ĭ好
    -0.23
    èµĭäºĪ
    -0.23
    åºĶä»ĺ
    -0.23
    ä¸ĢçĶŁ
    -0.23
    ä¹ħ
    -0.22
    æ·ĺ
    -0.22
    鸩
    -0.22
     equival
    -0.22
    ä»°
    -0.21
    POSITIVE LOGITS
    æĺ¨
    0.28
     chapel
    0.25
     pamph
    0.25
    scheduled
    0.24
    rail
    0.24
     proceedings
    0.23
     arrang
    0.23
    ष
    0.23
    ",-
    0.23
    å½ĵåľ°æŶéĹ´
    0.23
    Activations Density 0.002%

    No Known Activations