© 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. 663
    Prev
    Next
    INDEX
    Explanations

    CPU processing unit

    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
     postings
    -0.22
    çļĦä½ľåĵģ
    -0.22
    ä½ľåĵģ
    -0.22
    é¹Ĭ
    -0.21
    /rem
    -0.21
     indef
    -0.21
    /themes
    -0.21
     grocery
    -0.21
     decor
    -0.21
    ness
    -0.21
    POSITIVE LOGITS
    /cpu
    0.26
    (cpu
    0.25
    orra
    0.25
    头ä¸Ĭ
    0.24
    åĺ§
    0.24
    assis
    0.24
    çĶŁåij½
    0.23
    çĶŁåij½çļĦ
    0.23
    æł¸
    0.23
    åıĬåħ¶
    0.23
    Activations Density 0.285%

    No Known Activations