© 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. 486
    Prev
    Next
    INDEX
    Explanations

    greater than

    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
    çݩ家们
    -0.29
    åĩºçīĪ社
    -0.27
    -ish
    -0.27
    åĨį次
    -0.26
    人æ°Ķ
    -0.26
    åį´åıĪ
    -0.26
    çķĻè¨ĢæĿ¿
    -0.26
     cheap
    -0.25
     Kickstarter
    -0.25
    æĪªåĽ¾
    -0.25
    POSITIVE LOGITS
     supervisor
    0.37
     superv
    0.33
     supervise
    0.33
     Supervisor
    0.33
     Superv
    0.30
    æĮīè§Ħå®ļ
    0.30
     supervised
    0.29
     Administrative
    0.29
     assigned
    0.29
     supervision
    0.29
    Activations Density 0.021%

    No Known Activations