© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 493
    Prev
    Next
    INDEX
    Explanations

    millipedes, medicinal, acid

    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
    Architecture
    -0.24
    天èĬ±
    -0.24
    å°ijæķ°æ°ijæĹı
    -0.24
    èĢĦ
    -0.24
    çļĩåŃIJ
    -0.23
     epit
    -0.23
     ethnic
    -0.23
    山寨
    -0.23
    çŁŃæĿ¿
    -0.23
    è¶ĭåĬ¿
    -0.23
    POSITIVE LOGITS
    èļ¯
    0.36
    èļĵ
    0.31
    粪
    0.30
     worms
    0.26
    çĹĶ
    0.26
     mud
    0.25
    ç£ģ
    0.25
    è¹
    0.24
     Mud
    0.24
    æ²¼
    0.24
    Activations Density 0.010%

    No Known Activations