© 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. 553
    Prev
    Next
    INDEX
    Explanations

    ball into / away / from / on / in / to / up / at

    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
     metals
    -0.25
    æİ£
    -0.24
     thần
    -0.23
    é²ľ
    -0.23
    çģ¿
    -0.23
     phép
    -0.23
    代表
    -0.22
    è¿Ļæł·çļĦè¯Ŀ
    -0.22
     universal
    -0.21
    paces
    -0.21
    POSITIVE LOGITS
    iners
    0.26
    å²Ķ
    0.25
    into
    0.24
    çĶŁäº§æĢ»
    0.24
    inous
    0.23
     Blackjack
    0.23
    inge
    0.22
    breaker
    0.22
    egis
    0.22
    ifu
    0.22
    Activations Density 0.003%

    No Known Activations