© 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. 2806
    Prev
    Next
    INDEX
    Explanations

    nipples, pussy, juices, gland

    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
    åIJĦèĩª
    -0.23
    nable
    -0.23
    åĩŃ
    -0.22
    为空
    -0.22
    ror
    -0.22
    liness
    -0.22
     Apprentice
    -0.21
    bite
    -0.21
    ilda
    -0.21
     Boulder
    -0.20
    POSITIVE LOGITS
    åıĭæĥħéĵ¾æİ¥
    0.23
    ted
    0.23
    _STREAM
    0.22
    æ©Ľ
    0.22
    姥
    0.22
    橹
    0.20
    -aligned
    0.20
     getchar
    0.20
    tog
    0.20
    ized
    0.20
    Activations Density 0.003%

    No Known Activations