© 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. 16633
    Prev
    Next
    INDEX
    Explanations

    convenient

    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
    åħ³äºİæĪij们
    -0.19
    åĽłä¸ºåľ¨
    -0.17
    篾
    -0.17
    峦
    -0.17
    èħ±
    -0.17
    è¡·
    -0.17
    lasses
    -0.17
    arde
    -0.16
    ãģ¾ãģ¾
    -0.16
    edes
    -0.16
    POSITIVE LOGITS
    สà¸ļาย
    0.21
    å¿«æį·
    0.19
    -looking
    0.18
    ìĤ¬íķŃ
    0.17
    ously
    0.17
    æĹłæ¯Ķ
    0.17
     иÑģполÑĮзованиÑı
    0.17
    ricular
    0.16
    LY
    0.16
    icular
    0.16
    Activations Density 0.014%

    No Known Activations