© 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. 50823
    Prev
    Next
    INDEX
    Explanations

    family members: children, sons, daughters

    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
    ä¹ħ
    -0.09
    åĨįä¹Łæ²¡æľī
    -0.09
    OST
    -0.08
    opi
    -0.08
    åĤij
    -0.08
    ç°§
    -0.08
    èIJ¥ä¸ļé¢Ŀ
    -0.08
    åİŁå§ĭ
    -0.08
    uario
    -0.08
    é¬ĺ
    -0.08
    POSITIVE LOGITS
     Mud
    0.09
    æ¯Ĺ
    0.09
    åIJįåŃĹ
    0.09
    ç¾¼
    0.09
    çIJħ
    0.08
    åŃIJåŃĻ
    0.08
    /preferences
    0.08
    ä¿Ŀå¯Ĩ
    0.08
    lux
    0.08
    æ¿Ģ
    0.08
    Activations Density 0.063%

    No Known Activations