© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54034
    Prev
    Next
    INDEX
    Explanations

    complaints and pity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ä¼Ĺ
    -0.11
    缮
    -0.10
    åĴĮçĿ¦
    -0.09
    çłĶ究表æĺİ
    -0.09
    éĢıæĺİ
    -0.09
    æ°ijå¿ĥ
    -0.09
    éĢģä¸Ĭ
    -0.09
    ëĭµ
    -0.09
    çĤ¯
    -0.08
    ãģĿãģĨãģ§
    -0.08
    POSITIVE LOGITS
    æĬ±æĢ¨
    0.21
     complaining
    0.15
    è´
    0.14
     complaint
    0.13
    æĤ²è§Ĥ
    0.12
     Complaint
    0.12
    æĢ¨
    0.12
    æ¶Īæŀģ
    0.12
    æĦŁåı¹
    0.11
     complained
    0.11
    Activations Density 0.067%

    No Known Activations