© 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. 10995
    Prev
    Next
    INDEX
    Explanations

    gone viral

    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
    ugin
    -0.26
    æĹĮ
    -0.23
    å®Ħ
    -0.21
    游æĪıè£ħå¤ĩ
    -0.21
    ullets
    -0.20
    BOSE
    -0.20
    èĢģèĻİæľº
    -0.20
    _checkpoint
    -0.19
    æĬ½çĥŁ
    -0.19
    _native
    -0.19
    POSITIVE LOGITS
    çݰ象
    0.32
    ä¸Ģå¤ľ
    0.31
     phenomenon
    0.31
     viral
    0.30
    çĹħæ¯Ĵ
    0.26
     phenomena
    0.26
     memes
    0.26
    æİĢèµ·
    0.26
    è¿ħéĢŁ
    0.25
    å¼ķåıij
    0.25
    Activations Density 0.078%

    No Known Activations