© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 208
    Prev
    Next
    INDEX
    Explanations

    forming conclusions or diagnostic inferences

    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
    é¦ĸ次
    -0.27
    å¼Ģæĭĵ
    -0.26
    空åīį
    -0.24
    æ¸ħæ¾Ī
    -0.23
     officer
    -0.22
    ç±į
    -0.21
     donated
    -0.21
    è°ĥè¯ķ
    -0.21
     Updated
    -0.21
    gettext
    -0.21
    POSITIVE LOGITS
     conclusions
    0.48
    ç»ĵ论
    0.47
    å¾Ĺåĩº
    0.39
     assumptions
    0.35
     conclusion
    0.34
    åĽłæŀľ
    0.33
    åĪ¤æĸŃ
    0.33
    è¯ĦåĪ¤
    0.31
    å½Ĵ纳
    0.31
     rash
    0.30
    Activations Density 0.044%

    No Known Activations