© 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. 11388
    Prev
    Next
    INDEX
    Explanations

    runtime, duration, length

    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
     Geile
    -0.21
     ÐŁÐ¾Ñĩем
    -0.21
     ÐIJлекÑģан
    -0.21
    ectors
    -0.21
    å¸ĸåŃIJ
    -0.20
    Ĭ¶
    -0.20
     ÐĶмиÑĤÑĢ
    -0.19
    .Enum
    -0.19
     неÑģколÑĮки
    -0.19
    ÑĩÑĢежден
    -0.19
    POSITIVE LOGITS
    éķ¿çŁŃ
    0.28
    å½ķåĥı
    0.22
    ç£ħ
    0.21
     duration
    0.20
    (duration
    0.20
    æŀĦçŃij
    0.20
    leo
    0.19
    -length
    0.19
     fle
    0.19
    éķ¿åº¦
    0.19
    Activations Density 0.009%

    No Known Activations