© 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. 11159
    Prev
    Next
    INDEX
    Explanations

    official statements or releases

    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
    槽
    -0.23
    rid
    -0.20
     fot
    -0.19
     fol
    -0.19
    éĿ¢è¯ķ
    -0.18
     impro
    -0.18
    åĽłä¸ºæĪij
    -0.18
    âĹĦ
    -0.17
    åĬ©
    -0.17
    ta
    -0.17
    POSITIVE LOGITS
    åħ¬åijĬ称
    0.24
    ðŁĵ¢
    0.23
    宣å¸ĥ
    0.22
    å®ĺæĸ¹å¾®åįļ
    0.22
    æ¶Īæģ¯ç§°
    0.21
    æĹ¥æŃ£å¼ı
    0.21
     بÙĬاÙĨ
    0.21
    åıijå¸ĥäºĨ
    0.21
    åħ¬åijĬ
    0.20
    éĢļåijĬ
    0.20
    Activations Density 0.021%

    No Known Activations