© 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. 2766
    Prev
    Next
    INDEX
    Explanations

    granted by writing

    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
    æ·¬
    -0.26
    大çīĩ
    -0.23
    磨
    -0.23
    æ´ŀ
    -0.23
    å¸ĮæľĽèĩªå·±
    -0.23
    å¥Ķè·ij
    -0.23
     trailing
    -0.22
    idia
    -0.21
    è·¨
    -0.21
    Genres
    -0.21
    POSITIVE LOGITS
    åı¦æľī
    0.33
     elsewhere
    0.31
    ä¾µçĬ¯
    0.28
    åħ¶ä»ĸçļĦ
    0.27
    åѦåİĨ
    0.26
     other
    0.25
    æĿ¡è§Ħå®ļ
    0.24
    åħ¶å®ĥ
    0.24
     dis
    0.23
    here
    0.23
    Activations Density 0.071%

    No Known Activations