© 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. 14116
    Prev
    Next
    INDEX
    Explanations

    asking about specific interests

    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
    æ°¸
    -0.22
    èłĸ
    -0.19
     rowspan
    -0.19
    çļĦåŃĺåľ¨
    -0.19
    ä¸įç®¡ä½ł
    -0.19
    å©
    -0.19
    æ°¸è¿ľ
    -0.18
    defaults
    -0.18
    代价
    -0.17
     Dec
    -0.17
    POSITIVE LOGITS
     specific
    0.35
    æĥ³çŁ¥éģĵ
    0.33
    åħ·ä½ĵçļĦ
    0.33
    æĥ³è¦ģ
    0.31
    çī¹å®ļ
    0.31
    åħ·ä½ĵ
    0.30
     particular
    0.29
     конкÑĢеÑĤ
    0.29
    pecific
    0.28
    æĥ³æī¾
    0.28
    Activations Density 0.036%

    No Known Activations