© 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. 11013
    Prev
    Next
    INDEX
    Explanations

    company or corporation name

    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
    å°ijä¸įäºĨ
    -0.22
    éĹ©
    -0.20
    imm
    -0.19
    ici
    -0.19
    èħ´
    -0.19
    æĥ©
    -0.19
    å¿ĥæĢĿ
    -0.19
    åľ°æĸ¹
    -0.18
    ILD
    -0.18
    ensi
    -0.18
    POSITIVE LOGITS
    å®ŀéĻħæݧåĪ¶
    0.26
    æ²½
    0.22
    æĬķèµĦèĢħ
    0.22
    æĬ«éľ²
    0.21
    agara
    0.21
    ugin
    0.21
    åĪĽå§ĭ
    0.20
    æݧèĤ¡èĤ¡ä¸ľ
    0.20
    宣称
    0.19
     showc
    0.19
    Activations Density 0.038%

    No Known Activations