© 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. 12440
    Prev
    Next
    INDEX
    Explanations

    unpublished manuscripts and communications

    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
    æľ¬æľŁ
    -0.23
    aan
    -0.19
    éĸ±
    -0.19
    aN
    -0.19
    ç£Ķ
    -0.18
    çªĴ
    -0.18
     Tune
    -0.18
    миÑĢ
    -0.18
    ç¡Ŀ
    -0.18
    .constructor
    -0.18
    POSITIVE LOGITS
    å¾ħ
    0.23
     Kale
    0.21
    chema
    0.19
    åħĪè¡Į
    0.19
    èĩªåľ¨
    0.19
    æľªæĪIJ
    0.18
    çĶŁèĤĸ
    0.18
    èģĶç³»æĸ¹å¼ı
    0.18
    éĥ¨èIJ½
    0.18
    IGIN
    0.18
    Activations Density 0.100%

    No Known Activations