© 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. 1038
    Prev
    Next
    INDEX
    Explanations

    date and time

    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
    å¿ĥå¾Ĺ
    -0.23
    SRC
    -0.23
    飨
    -0.22
    RIPT
    -0.22
    è¦ģä¸įè¦ģ
    -0.21
    .ua
    -0.21
    ERING
    -0.21
    _hooks
    -0.21
    uron
    -0.21
    CRY
    -0.21
    POSITIVE LOGITS
    ä¸ºæľŁ
    0.32
     fully
    0.27
     either
    0.26
     ~
    0.26
    ç«ĭ
    0.25
    åħĪæĺ¯
    0.25
     TBD
    0.25
    æ¯ı个
    0.24
    ä½Ĩä¸įéĻIJäºİ
    0.24
    åİŁåĪĻä¸Ĭ
    0.24
    Activations Density 0.043%

    No Known Activations