© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12948
    Prev
    Next
    INDEX
    Explanations

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ón
    -0.20
    erin
    -0.20
    åľ¨æł¡
    -0.18
    å®ŀéĻħæݧåĪ¶
    -0.17
    ä¸Ģ身
    -0.17
    泡
    -0.17
    æĴ¤
    -0.17
    åij£
    -0.17
    èĩªèº«
    -0.17
    ãģ£ãģĵ
    -0.17
    POSITIVE LOGITS
    æĻĤåĢĻ
    0.22
    ãģ¾ãģķãģ«
    0.20
    对åħ¶çľŁå®ŀ
    0.20
    åĽłä¸ºæĪij
    0.19
    æŶåĢĻ
    0.19
    æĸ°å½¢åĬ¿ä¸ĭ
    0.19
    éģ©åIJĪ
    0.18
    å¹´é¾Ħ段
    0.18
    åħ¸åŀĭçļĦ
    0.18
    éļĶçĿĢ
    0.17
    Activations Density 0.065%

    No Known Activations