© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    place names and context

    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
    æľĢéĢĤåIJĪ
    -0.27
    -rounded
    -0.27
     incorpor
    -0.27
    èĩªçĦ¶èĢĮçĦ¶
    -0.26
    å¡ijéĢł
    -0.24
     smarter
    -0.24
    åįĵè¶Ĭ
    -0.24
    æĽ´éĢĤåIJĪ
    -0.24
    èĥ½åĬĽåĴĮ
    -0.24
    Å©
    -0.24
    POSITIVE LOGITS
    äºĭåıij
    0.35
    èѦæĸ¹
    0.32
     suspected
    0.31
    éĻĦè¿ijçļĦ
    0.30
    å¼ķåıijäºĨ
    0.30
    äºĭæķħåıijçĶŁ
    0.29
    éĻĦè¿ij
    0.29
    å½ĵæĻļ
    0.29
     victim
    0.28
     incidents
    0.28
    Activations Density 0.137%

    No Known Activations