© 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. 16573
    Prev
    Next
    INDEX
    Explanations

    conversation and discussion

    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
    æīĵåĮħ
    -0.23
    认è¯ĨåĪ°
    -0.20
    貫
    -0.19
    éģįå¸ĥ
    -0.19
    å¿ĥæĦı
    -0.18
    emaker
    -0.18
    éĽĩ
    -0.17
    èĭ¦èĭ¦
    -0.17
    nameof
    -0.17
    _Internal
    -0.17
    POSITIVE LOGITS
    è¯Ŀé¢ĺ
    0.47
     conversation
    0.46
    对è¯Ŀ
    0.42
    交æµģ
    0.41
    交è°Ī
    0.41
    åıijè¨Ģ
    0.38
    讨论
    0.35
     conversations
    0.35
     discussion
    0.35
    è°Ī论
    0.35
    Activations Density 0.149%

    No Known Activations