© 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. 13040
    Prev
    Next
    INDEX
    Explanations

    date, time, or file separators

    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
     ÐŁÐ¾Ñĩем
    -0.24
     ÐIJлекÑģан
    -0.24
     ÐĶмиÑĤÑĢ
    -0.24
    irement
    -0.21
     ÐĶм
    -0.20
     поÑģколÑĮ
    -0.19
    åĨ¬å¤©
    -0.19
    竦
    -0.19
    icans
    -0.19
    ican
    -0.18
    POSITIVE LOGITS
    æĶ¯çº¿
    0.20
    å½ĵåľ°æŶéĹ´
    0.20
    åħĪè¿ĽæĬĢæľ¯
    0.18
    æİ£
    0.18
    çĶµä¿¡
    0.18
    é¢ijéģĵ
    0.18
    éĶĢåĶ®æ¸łéģĵ
    0.18
    æĬĢæľ¯æĶ¯æĮģ
    0.18
    Collapsed
    0.18
    çĶµæ°Ķ
    0.18
    Activations Density 0.128%

    No Known Activations