© 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. 57645
    Prev
    Next
    INDEX
    Explanations

    power play goals

    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
    çļĦåij½è¿IJ
    -0.09
    羣缸
    -0.09
    æ¸ħæī«
    -0.09
    éķŃ
    -0.09
    æīĵä»Ĺ
    -0.09
    çīĩéĿ¢
    -0.08
    èĭ±åĭĩ
    -0.08
    å¸Ĥåľºç«ŀäºī
    -0.08
    èı
    -0.08
    Americ
    -0.08
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.10
    æĭĽ
    0.09
    uyá»ģn
    0.09
    å®ļä½į
    0.09
    ter
    0.09
    -prev
    0.08
    磬
    0.08
     revital
    0.08
    çİīçŁ³
    0.08
    irut
    0.08
    Activations Density 0.001%

    No Known Activations