© 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. 13938
    Prev
    Next
    INDEX
    Explanations

    PCT/US

    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
    ing
    -0.18
    inality
    -0.17
    alink
    -0.17
    åħ¶éĹ´
    -0.17
    ongo
    -0.17
    æĭīä¸ģ
    -0.17
     ongoing
    -0.16
    izz
    -0.16
    alten
    -0.16
    çĽij管éĥ¨éŨ
    -0.16
    POSITIVE LOGITS
    è§Ĥ
    0.20
    æįķæįī
    0.19
    带走
    0.18
    è¿İæĿ¥
    0.18
    è¿Ļä¸ªåľ°æĸ¹
    0.18
    æī¿è½½
    0.18
    zym
    0.17
    ä»ĬæĻļ
    0.17
    æ¹ĥ
    0.17
     gerade
    0.17
    Activations Density 0.001%

    No Known Activations