© 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. 2845
    Prev
    Next
    INDEX
    Explanations

    fine, perfect, great

    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
    éĩijåŃĹå¡Ķ
    -0.26
    åīįåIJİ
    -0.24
    äºĴåĬ©
    -0.24
    亮
    -0.24
     flank
    -0.24
    èī¯
    -0.23
    æīĭåĬ¿
    -0.22
    åĪĨåĪ«ä¸º
    -0.22
    尺寸
    -0.22
    ghi
    -0.22
    POSITIVE LOGITS
    åĽłä¸ºå¥¹
    0.24
    åĽłä¸ºæĪij们
    0.24
     Penguins
    0.24
    è¿Ļåıªæĺ¯
    0.23
     because
    0.23
    çijķ
    0.23
    ness
    0.22
     Exc
    0.22
     exc
    0.21
    å®ģ
    0.21
    Activations Density 0.022%

    No Known Activations