© 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. 1293
    Prev
    Next
    INDEX
    Explanations

    datasheet documentation

    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
     Captain
    -0.29
    helm
    -0.28
     televis
    -0.28
     Attendance
    -0.27
     Newspaper
    -0.26
     trainers
    -0.26
     Entertainment
    -0.26
    éĢļé£İ
    -0.25
     scripted
    -0.25
     entertainment
    -0.25
    POSITIVE LOGITS
    åĻ¨ä»¶
    0.45
    èĬ¯çīĩ
    0.38
     Semiconductor
    0.34
     semiconductor
    0.34
    éĽĨæĪIJçĶµè·¯
    0.33
     resistor
    0.31
     datas
    0.31
    è¿Ļç±»
    0.30
     chip
    0.30
    åįĬ导ä½ĵ
    0.29
    Activations Density 0.182%

    No Known Activations