© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35586
    Prev
    Next
    INDEX
    Explanations

    persons with

    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
    å¤ł
    -0.10
    ãĥ¼ãĤ¿ãĥ¼
    -0.10
    ster
    -0.09
    ermann
    -0.08
    ä»ij
    -0.08
    æį¡
    -0.08
    изаÑĤоÑĢ
    -0.08
    ÑĢоÑģÑĤ
    -0.08
    ãģ£ãģ
    -0.08
    Õ²
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.11
    nard
    0.10
    ê¹IJ
    0.10
    entes
    0.09
    forth
    0.09
    ively
    0.09
    ãģĹãģ¾ãģĨ
    0.08
    quito
    0.08
    åľ¨æĪijçļĦ
    0.08
    itez
    0.08
    Activations Density 0.086%

    No Known Activations