© 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. 33327
    Prev
    Next
    INDEX
    Explanations

    continues until

    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
    æĪijä¸įæĥ³
    -0.10
    виÑĤ
    -0.09
    çŃīçĿĢ
    -0.09
    åĮĻ
    -0.08
     vej
    -0.08
    çļĦåıijçĶŁ
    -0.08
    纸ä¸Ĭ
    -0.08
    éĶ¹
    -0.08
    çļĦç«ŀäºī
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ缴åĪ°
    0.15
    éļıåIJİ
    0.13
    æѤåIJİ
    0.13
    缴åĪ°
    0.12
     subsequently
    0.12
    缴èĩ³
    0.12
    åIJİæĿ¥
    0.11
     ensuite
    0.11
     subsequent
    0.10
     thereafter
    0.10
    Activations Density 0.186%

    No Known Activations