© 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. 14083
    Prev
    Next
    INDEX
    Explanations

    same / exclusively / together

    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
    èĦĬ
    -0.21
    æī©å®¹
    -0.21
    ä¹Łæĺ¯å¾Ī
    -0.21
    å¢ħ
    -0.21
    индивид
    -0.20
    縻
    -0.20
    _INLINE
    -0.20
    æĦ¿æĻ¯
    -0.20
    INLINE
    -0.20
    ä¹Łæĺ¯å¦ĤæѤ
    -0.19
    POSITIVE LOGITS
    ither
    0.21
    çļĦéĤ£ç§į
    0.21
    tl
    0.20
    opr
    0.19
    åħħåĪĨåıijæĮ¥
    0.19
    失åİ»
    0.18
     communic
    0.18
     unveil
    0.18
    ious
    0.18
     offices
    0.18
    Activations Density 0.555%

    No Known Activations