© 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. 2156
    Prev
    Next
    INDEX
    Explanations

    ceasing or not happening

    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
    æµ£
    -0.23
    éĢīèĤ¡
    -0.23
    çIJĨ解åĴĮ
    -0.23
    -next
    -0.23
     strategy
    -0.22
    _shuffle
    -0.22
    åĿIJçĿĢ
    -0.22
    棣
    -0.22
     evening
    -0.22
    ,next
    -0.22
    POSITIVE LOGITS
    æ¶Ī失
    0.45
     abandoned
    0.39
     disappeared
    0.38
    æIJģ
    0.36
    æ¶Ī失äºĨ
    0.35
     abandon
    0.35
    æĿ³
    0.34
     discontinued
    0.33
    æ´»è·ĥ
    0.32
    å¼ĥ
    0.32
    Activations Density 0.213%

    No Known Activations