© 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. 57537
    Prev
    Next
    INDEX
    Explanations

    prints dimensions

    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
    åĪ¤
    -0.09
    éģĩä¸Ĭ
    -0.09
    åłĨ积
    -0.08
    鸨
    -0.08
    æ´Ĺå¹²åĩĢ
    -0.08
     Stopwatch
    -0.08
    stdin
    -0.08
     deaf
    -0.08
    æī¹
    -0.08
    å®ĺåı¸
    -0.08
    POSITIVE LOGITS
    æĤ¬æĮĤ
    0.11
    æĻļé¤IJ
    0.11
    æĮĤ
    0.10
    æ°¸ä¹ħ
    0.10
    hang
    0.10
     hang
    0.10
    åºĩ
    0.10
    å®ŀçĶ¨æĢ§
    0.10
    çŀij
    0.10
    èµ°å»Ĭ
    0.09
    Activations Density 0.111%

    No Known Activations