© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12432
    Prev
    Next
    INDEX
    Explanations

    names, states, currencies, and numbers

    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
    exo
    -0.19
    å¤Ħ
    -0.18
    %s
    -0.17
    æİ¥
    -0.17
    âĿĹ
    -0.16
     “
    -0.16
    å®ļæľŁ
    -0.16
     merry
    -0.15
    -fontawesome
    -0.15
    åĽ¾è¡¨
    -0.15
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.21
    edList
    0.21
    èĢģ人家
    0.21
    jiang
    0.20
    èµ·è¯ī
    0.19
    颧
    0.19
    è§Ħ模æľĢ大
    0.18
    çŁ¥éģĵèĩªå·±
    0.18
    害ç¾ŀ
    0.17
    æij§æ¯ģ
    0.17
    Activations Density 0.044%

    No Known Activations