© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    especially when traveling

    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
    åıĪ被
    -0.29
    ç»ıåİĨäºĨ
    -0.23
    Unnamed
    -0.23
    ä»ĸåıĪ
    -0.23
    unique
    -0.23
    Serialization
    -0.22
    æīĢ以ä»ĸ
    -0.22
    äºĨä»ĸçļĦ
    -0.21
    ä½Ĩä»ĸ
    -0.21
    ç»ĵæŀľæĺ¾ç¤º
    -0.21
    POSITIVE LOGITS
    å°½éĩı
    0.41
    éģ¿åħį
    0.40
    å°½åı¯èĥ½
    0.38
    ä¸įè¦ģ
    0.38
    以åħį
    0.36
    ä¸įè¦ģ太
    0.35
    ç¡®ä¿Ŀ
    0.33
     yourself
    0.33
     avoid
    0.32
    ä¹Łä¸įè¦ģ
    0.31
    Activations Density 0.035%

    No Known Activations