© 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. 22674
    Prev
    Next
    INDEX
    Explanations

    deep voice

    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
    çĹĽ
    -0.10
    æݸ
    -0.09
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    é»ī
    -0.09
    ä¿®çIJĨ
    -0.09
    å·į
    -0.09
    è¦ģéĹ»
    -0.09
     skirm
    -0.09
    åħ¨æĹ¥åĪ¶
    -0.08
    æĶ¾æīĭ
    -0.08
    POSITIVE LOGITS
    å£°éŁ³
    0.17
    çļĦå£°éŁ³
    0.15
     voice
    0.15
     voices
    0.13
     голоÑģ
    0.12
     giá»įng
    0.11
    voice
    0.11
    èģ²éŁ³
    0.11
    çĨŁæĤīçļĦ
    0.11
     voz
    0.10
    Activations Density 0.035%

    No Known Activations