© 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. 50167
    Prev
    Next
    INDEX
    Explanations

    network, magazine, or tracks

    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
    åij½ä¸Ń
    -0.10
    tro
    -0.09
    éĥħ
    -0.09
    çŀ»
    -0.09
    ä»ħä¾Ľ
    -0.09
    å®ł
    -0.09
    HEMA
    -0.09
    DMA
    -0.08
    illum
    -0.08
    éĺĹ
    -0.08
    POSITIVE LOGITS
    éĿĴå¹´
    0.10
    å§IJ妹
    0.10
    è¾¹ç¼ĺ
    0.10
    å°ıé¢Ŀ
    0.09
    ç»´æĿĥ
    0.09
    人æĿĥ
    0.09
    乡æĿij
    0.09
    à¹Ģย
    0.09
    讲å¸Ī
    0.08
    æĢ§åĪ«
    0.08
    Activations Density 0.132%

    No Known Activations