© 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. 27012
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    åıĺå¾Ĺ
    -0.10
    è¦ģä¹Ī
    -0.09
    è´²
    -0.09
    å°ıä¼Ļä¼´
    -0.09
    çĭĤ欢
    -0.09
    æĪ¾
    -0.09
     pik
    -0.08
    æĸ§
    -0.08
    çĵ¶é¢Ī
    -0.08
    æ¤Ĵ
    -0.08
    POSITIVE LOGITS
    abar
    0.10
    AGR
    0.09
    TemplateName
    0.09
    ä¸Ķ
    0.09
    åĽŀçŃĶ
    0.09
    ä¸Ģæŀļ
    0.08
     Russo
    0.08
    âĮĢ
    0.08
    æĨ¬
    0.08
    eter
    0.08
    Activations Density 0.007%

    No Known Activations