© 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. 13243
    Prev
    Next
    INDEX
    Explanations

    selection of items from a list

    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
    çľĭä¸įè§ģ
    -0.19
    å·²ç»ıè¾¾åĪ°
    -0.18
    .addChild
    -0.18
    æ§Į
    -0.18
    æ¸ĹéĢı
    -0.18
    è¿Ļ个æĹ¶ä»£
    -0.18
     Packing
    -0.18
    èĬ
    -0.18
    contents
    -0.17
    _HS
    -0.17
    POSITIVE LOGITS
    çŃĽéĢī
    0.38
    æ·ĺæ±°
    0.30
    åIJįåįķ
    0.29
     lá»įc
    0.29
    åħ¥åĽ´
    0.29
    åĢĻéĢī
    0.29
    éĢīåĩº
    0.28
    åıªåī©ä¸ĭ
    0.28
    è¿ĩ滤
    0.27
     selection
    0.27
    Activations Density 0.177%

    No Known Activations