© 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. 15783
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    è²Į
    -0.25
    è¯ģåĪ¸äº¤æĺĵ
    -0.21
    _RM
    -0.19
    åŁºæľ¬æĥħåĨµ
    -0.19
    å½»
    -0.18
    ä¸Ģ缴åĪ°
    -0.17
    åħ¨è¿ĩç¨ĭ
    -0.17
    åĹŁ
    -0.17
    çĶ³è¯ī
    -0.17
    /ar
    -0.17
    POSITIVE LOGITS
    è¿Ļåı¥è¯Ŀ
    0.20
    åıijå¸ĥä¼ļä¸Ĭ
    0.20
    eras
    0.19
    è¿Ļè¯Ŀ
    0.18
    hiba
    0.18
    ONENT
    0.18
    conut
    0.18
    errer
    0.18
    形容
    0.18
     elabor
    0.18
    Activations Density 0.044%

    No Known Activations