© 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. 29
    Prev
    Next
    INDEX
    Explanations

    months, dates, and publication descriptors

    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
    ington
    -0.23
    KeyEvent
    -0.22
    åłĤ
    -0.22
    erner
    -0.22
    ÑĤÑĮÑģÑı
    -0.21
    åħ¬åħ±åľºæīĢ
    -0.21
     prer
    -0.21
    _ALIGN
    -0.21
    _unix
    -0.21
    å¾ģæĶ¶
    -0.20
    POSITIVE LOGITS
    çģµæĦŁ
    0.28
    é¢Ĩçķ¥
    0.25
     spor
    0.23
     ва
    0.23
    on
    0.22
    èį¯æĿIJ
    0.22
    Reuse
    0.22
    æ¶Īè´¹éľĢæ±Ĥ
    0.21
    æĮ£æīİ
    0.21
    stud
    0.21
    Activations Density 0.005%

    No Known Activations