© 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. 12970
    Prev
    Next
    INDEX
    Explanations

    animal shelter or stray kittens

    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
    è¡Įäºĭ
    -0.20
    ä¸Ĭåįĩ
    -0.20
    æ°´æµģ
    -0.20
    åľ¨çݩ家ä¸Ń
    -0.19
    ollar
    -0.19
    [loc
    -0.18
     Binding
    -0.18
    Ǿ
    -0.18
    蹩
    -0.18
    åĽłç´ł
    -0.18
    POSITIVE LOGITS
     ghé
    0.22
    ä¼ĺåħĪ
    0.21
     вок
    0.21
     healed
    0.21
    ieve
    0.20
    个åĪ«
    0.20
    伤çĹħ
    0.20
    æĢ»éĺŁ
    0.20
    çIJĨäºĭä¼ļ
    0.19
     PIT
    0.19
    Activations Density 0.015%

    No Known Activations