© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    menu option instructions

    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
     trib
    -0.23
    ders
    -0.21
    amb
    -0.21
    imb
    -0.21
    ilk
    -0.20
     popular
    -0.20
    åIJĪ
    -0.20
    aison
    -0.20
    apel
    -0.19
    popular
    -0.18
    POSITIVE LOGITS
    第ä¸ĢæŃ¥
    0.24
     pornôs
    0.24
    è¦ģåģļåĪ°
    0.23
     pornô
    0.23
    æŁ¥æĺİ
    0.23
    对çĿĢ
    0.22
    TOOLS
    0.21
     bezpo
    0.21
     tjejer
    0.21
     salopes
    0.21
    Activations Density 0.189%

    No Known Activations