© 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. 16167
    Prev
    Next
    INDEX
    Explanations

    update or transition from old

    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
    以èī²
    -0.23
    æ¬ł
    -0.22
     commune
    -0.20
    å°ıä¼Ļ
    -0.19
    æľīæŶåĢĻ
    -0.19
    éĤ£äºº
    -0.19
    zo
    -0.18
    人çĶŁçļĦ
    -0.18
    æ¥Ĥ
    -0.18
    otp
    -0.18
    POSITIVE LOGITS
    转åŀĭ
    0.39
    æŧ
    0.39
    è¿ĩ渡
    0.38
    è¿ģ移
    0.38
     transition
    0.35
    åİŁæľī
    0.35
     пеÑĢеÑħод
    0.34
    (old
    0.34
     old
    0.33
    old
    0.32
    Activations Density 0.244%

    No Known Activations