© 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. 16474
    Prev
    Next
    INDEX
    Explanations

    hyphenated names

    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
    æľīæĦı
    -0.23
    çİīçŁ³
    -0.20
    çĶŁåŃĺ
    -0.20
    çĶļèĩ³
    -0.19
    FAST
    -0.19
    åĨħå¤ĸ
    -0.18
    æľºä¼ļ
    -0.18
    eph
    -0.17
    ging
    -0.17
    æĹłè¾ľ
    -0.17
    POSITIVE LOGITS
    ittle
    0.19
     minded
    0.18
    lek
    0.17
    URA
    0.17
    lest
    0.17
    ç»Ħç»ĩå®ŀæĸ½
    0.17
    è·¬
    0.17
    çªģåĩºéĹ®é¢ĺ
    0.16
    unbind
    0.16
    åĪĽæĸ°åŀĭ
    0.16
    Activations Density 0.090%

    No Known Activations