© 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. 776
    Prev
    Next
    INDEX
    Explanations

    quote marks

    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
    -être
    -0.28
    boarding
    -0.21
    /she
    -0.21
    ä¸įäºĨ
    -0.21
    è¿ĻäºĽä¸ľè¥¿
    -0.19
    oft
    -0.19
    è¿ĻäºĽéĹ®é¢ĺ
    -0.19
    oa
    -0.19
    买车
    -0.18
     Windsor
    -0.18
    POSITIVE LOGITS
    åľ¨
    0.29
    Â
    0.24
    entifier
    0.22
    es
    0.21
    0.20
    ãĢģ“
    0.19
     (
    0.18
    —
    0.18
    auty
    0.18
    åĿĬ
    0.18
    Activations Density 0.102%

    No Known Activations