© 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. 781
    Prev
    Next
    INDEX
    Explanations

    names of actors and musicians

    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
    çĿ¹
    -0.28
    å´¤
    -0.25
    soever
    -0.24
    ipse
    -0.24
    æݧåĪ¶ç³»ç»Ł
    -0.23
    ä¼Ļä¼´åħ³ç³»
    -0.23
    jmp
    -0.23
     UIS
    -0.23
    æľŁåĨħ
    -0.23
    typeid
    -0.22
    POSITIVE LOGITS
     beat
    0.28
    ç¼ĸåī§
    0.28
    导æ¼Ķ
    0.27
     singer
    0.27
    æŃĮæīĭ
    0.27
    æ¼ĶåĶ±
    0.27
    åıĶ
    0.27
     vocalist
    0.26
     lyric
    0.26
    èīºäºº
    0.26
    Activations Density 0.057%

    No Known Activations