© 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. 16684
    Prev
    Next
    INDEX
    Explanations

    here or you

    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
    å½»
    -0.22
    aged
    -0.22
    oret
    -0.21
    åijĹ
    -0.20
    éĩįéĩį
    -0.20
    å¾¹
    -0.19
    agg
    -0.19
    !/
    -0.18
    uids
    -0.18
    AGED
    -0.18
    POSITIVE LOGITS
     here
    0.31
    åľ¨è¿ĻéĩĮ
    0.26
    è¿ĻéĩĮ
    0.25
     здеÑģÑĮ
    0.23
    åľ¨æѤ
    0.23
     ÙĩÙĨا
    0.22
    æѤå¤Ħ
    0.22
    ä¸įåĨį
    0.21
    ãģĵãģĵãģ§
    0.21
     ÐĹдеÑģÑĮ
    0.20
    Activations Density 0.027%

    No Known Activations