© 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. 765
    Prev
    Next
    INDEX
    Explanations

    found, said, gave, was

    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
     tort
    -0.25
    é¾
    -0.23
     sed
    -0.23
    ancy
    -0.23
    <|endoftext|>
    -0.22
    èĦ
    -0.22
     complementary
    -0.22
     rightly
    -0.22
     messed
    -0.22
     complexity
    -0.21
    POSITIVE LOGITS
    åħijçİ°
    0.28
    两款
    0.27
    缮åīįå·²ç»ı
    0.27
    æĸ°æ¬¾
    0.24
    åıijè¨Ģ人
    0.24
    è°ĥæŁ¥æĺ¾ç¤º
    0.24
    æĹ¥åīį
    0.23
    æ¶Īæģ¯ç§°
    0.23
    æį®ä»ĭç»į
    0.23
    lÃŃ
    0.23
    Activations Density 0.575%

    No Known Activations