© 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. 12991
    Prev
    Next
    INDEX
    Explanations

    this week

    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
    yne
    -0.22
    æ¯ıå¹´
    -0.21
    å½ĵå¹´
    -0.20
     Jerome
    -0.18
    ·»
    -0.18
     Fac
    -0.18
    æľ¬èº«
    -0.18
    andler
    -0.18
    æĹłåĬĽ
    -0.18
     sund
    -0.18
    POSITIVE LOGITS
    æ»Ķ
    0.21
    eel
    0.20
    ä¸ĬéĻIJ
    0.19
    æĪijè¦ģ
    0.19
    åħ¹
    0.19
    çı£
    0.18
    主é¢ĺæķĻèĤ²
    0.18
    eil
    0.18
    çĪ±ç¾İ
    0.18
     Functional
    0.18
    Activations Density 0.030%

    No Known Activations