© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12438
    Prev
    Next
    INDEX
    Explanations

    than any other

    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
    é«ĺä»·
    -0.19
    ANGED
    -0.18
     apl
    -0.18
     Pays
    -0.18
    ä¸įä½ı
    -0.17
    bsub
    -0.17
    åħ¨èµĦ
    -0.17
    lash
    -0.17
    æ©IJ
    -0.17
    é«ĺæ°´å¹³
    -0.17
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.23
    åħ¶å®ĥ
    0.22
    åħ¶ä»ĸ
    0.20
     whatsoever
    0.20
    mur
    0.19
    ounge
    0.19
     sonst
    0.19
    å¸Ńåį·
    0.19
    åħ¶ä»ĸçļĦ
    0.18
    çļĦåľ°æŃ¥
    0.18
    Activations Density 0.021%

    No Known Activations