© 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. 389
    Prev
    Next
    INDEX
    Explanations

    this or these followed by a noun

    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
    åĴĮåıijå±ķ
    -0.23
    /from
    -0.23
    ħĮ
    -0.22
    åħ¶å®ĥéĹ®é¢ĺ
    -0.22
     anew
    -0.21
     wanting
    -0.21
     Secrets
    -0.21
    èĢĮè¿Ļ
    -0.21
     eternity
    -0.21
     sez
    -0.21
    POSITIVE LOGITS
    家ä¼Ļ
    0.30
     function
    0.30
    æĺ¯ä¸Ģ
    0.24
    羣çļĦæĺ¯
    0.24
    	RTLU
    0.23
    traîn
    0.22
     ?>">č↵
    0.22
    åĩ½æķ°
    0.22
    INUE
    0.22
    arna
    0.22
    Activations Density 0.168%

    No Known Activations