© 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. 13485
    Prev
    Next
    INDEX
    Explanations

    impaired function or defects

    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
    ä¸įæĸŃåľ°
    -0.22
    åĪ¶åº¦æĶ¹éĿ©
    -0.20
    çĩĴ
    -0.19
    ervlet
    -0.19
    çĥ§
    -0.19
    fé
    -0.19
    ä¸įåģľåľ°
    -0.18
    æł¼å¤ĸ
    -0.18
    CLOSE
    -0.18
     صاÙĦ
    -0.18
    POSITIVE LOGITS
    ç¨ĭ度
    0.27
    导èĩ´
    0.24
     caused
    0.20
    éĢļ讯
    0.20
     due
    0.20
    æ®Ĩ
    0.19
    æĦ§
    0.19
    icap
    0.19
    ened
    0.18
     dere
    0.18
    Activations Density 0.411%

    No Known Activations