© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2063
    Prev
    Next
    INDEX
    Explanations

    industries and applications

    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
    åħļç»Ħ
    -0.24
    æĺŁæĺŁ
    -0.23
    rieve
    -0.23
    ä¸ºæł¸å¿ĥçļĦ
    -0.23
    .Cluster
    -0.22
    åĩłåı¥
    -0.22
    éĥ¨ä¸»ä»»
    -0.22
    åºı
    -0.21
    çļĦèĥ½åĬĽ
    -0.21
     fizz
    -0.21
    POSITIVE LOGITS
     alike
    0.32
    åľºåIJĪ
    0.28
     applications
    0.28
    çĶ¨éĢĶ
    0.27
    éľĢè¦ģçĶ¨åĪ°
    0.27
    个人
    0.26
     situations
    0.25
     hobby
    0.25
    éľĢè¦ģçĶ¨
    0.25
    any
    0.24
    Activations Density 0.279%

    No Known Activations