© 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. 16698
    Prev
    Next
    INDEX
    Explanations

    to processes or pharm

    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
     Kurd
    -0.20
    own
    -0.19
    ****************************************************************
    -0.19
    å¾Īéķ¿æŶéĹ´
    -0.19
    å½ĵæŶ
    -0.19
    è¿Ļå¥Ĺ
    -0.19
    æľ¬éĴ±
    -0.18
    ako
    -0.18
    èĢģçĻ¾å§ĵ
    -0.18
    产çĶŁäºĨ
    -0.18
    POSITIVE LOGITS
    åıĬ缸åħ³
    0.28
    æľīçļĦçݩ家
    0.21
    æļ¨
    0.21
    缸åħ³åĨħ容
    0.20
    ondere
    0.20
    åĴĮå®ĮåĸĦ
    0.19
    гÑĥ
    0.19
    修订
    0.19
    ulerAngles
    0.19
     Dare
    0.19
    Activations Density 0.188%

    No Known Activations