© 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. 1306
    Prev
    Next
    INDEX
    Explanations

    printed circuit boards

    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
     nighttime
    -0.31
     franchise
    -0.27
     quarry
    -0.26
    QueryString
    -0.26
     rentals
    -0.26
     Membership
    -0.26
    红éħĴ
    -0.26
     fencing
    -0.25
    èij¡èIJĦéħĴ
    -0.25
     Evening
    -0.24
    POSITIVE LOGITS
     solder
    0.60
    èĬ¯çīĩ
    0.43
    çĦĬ
    0.43
    åĻ¨ä»¶
    0.40
     Semiconductor
    0.37
    çĦĬæİ¥
    0.37
     PCB
    0.36
    çĶµè·¯
    0.36
     semiconductor
    0.35
     manufact
    0.34
    Activations Density 0.265%

    No Known Activations