© 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. 15256
    Prev
    Next
    INDEX
    Explanations

    hobbies and activities

    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
    æľºæŀĦ
    -0.21
    åħ³éŨ
    -0.19
    æŀ¶æŀĦ
    -0.19
    éħįåIJĪ
    -0.19
    ç¼ħçĶ¸
    -0.19
    ç»ĵæŀĦ
    -0.18
     getSupportActionBar
    -0.18
    ç¦ħ
    -0.18
    æĶ¿çŃĸæݪæĸ½
    -0.18
     Rubin
    -0.18
    POSITIVE LOGITS
    çĪ±å¥½
    0.33
     hobbies
    0.27
    åĸľå¥½
    0.26
    åĸľæ¬¢
    0.23
    åħ´è¶£
    0.23
    åģı好
    0.22
    èĪĪ趣
    0.22
     Activities
    0.21
    Activities
    0.21
    éĴ»çłĶ
    0.21
    Activations Density 0.037%

    No Known Activations