© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1569
    Prev
    Next
    INDEX
    Explanations

    torn, defeated, hunted

    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
    æĪ·å¤ĸ
    -0.33
     weekday
    -0.31
    åij¨æľ«
    -0.30
    åij¨ä¸Ģ
    -0.30
    çĨ¨
    -0.28
     moms
    -0.28
    çľĭçĶµè§Ĩ
    -0.28
     outdoor
    -0.28
    ä¸Ĭç½ij
    -0.28
    åij¨åħŃ
    -0.28
    POSITIVE LOGITS
    æ¯ģçģŃ
    0.48
    çģŃ亡
    0.43
    åıįæĬĹ
    0.43
    èĥĮåıĽ
    0.42
     mortal
    0.40
    å¤įä»ĩ
    0.40
     teleport
    0.40
     humanity
    0.39
    éĩį伤
    0.39
    é¦ĸé¢Ĩ
    0.39
    Activations Density 0.452%

    No Known Activations