© 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. 14171
    Prev
    Next
    INDEX
    Explanations

    Pokemon, units, lineup, Pet, Trainer

    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
    imedia
    -0.21
    ÑİÑĢ
    -0.21
    ç¾İèªī
    -0.20
    æī¿
    -0.19
    æĤĦçĦ¶
    -0.19
     Reid
    -0.18
    Insensitive
    -0.18
    idges
    -0.18
    ammer
    -0.18
    laces
    -0.18
    POSITIVE LOGITS
    éĺµå®¹
    0.23
    çĵ´
    0.23
    个æĢ§
    0.21
    æĬķåħ¥åĪ°
    0.21
    è®Ńç»ĥ
    0.21
     обÑĥÑĩ
    0.21
    å½¢æĢģ
    0.20
    æĪĺæĸĹ
    0.20
    æĻĻ
    0.20
    å®ŀæĪĺ
    0.20
    Activations Density 0.035%

    No Known Activations