© 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. 11953
    Prev
    Next
    INDEX
    Explanations

    as ... as

    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
    两年åīį
    -0.20
    å¼ķãģį
    -0.20
    æİ¥åıĹäºĨ
    -0.19
    #line
    -0.19
     Ded
    -0.19
    ä¸įä»ħä»ħæĺ¯
    -0.19
    StateException
    -0.19
    å°ıæŶåīį
    -0.18
    åĪĿ次
    -0.18
     vững
    -0.17
    POSITIVE LOGITS
     needed
    0.25
    ä½łè§īå¾Ĺ
    0.25
    èĩªåľ¨
    0.24
     freely
    0.24
    ä½łåĸľæ¬¢
    0.24
    éķ¿çŁŃ
    0.24
     whatever
    0.23
     whichever
    0.23
    èĩªå·±åĸľæ¬¢
    0.23
    needed
    0.22
    Activations Density 0.039%

    No Known Activations