© 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. 26790
    Prev
    Next
    INDEX
    Explanations

    voice assistant commands

    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
    æ®ī
    -0.09
    è¿«
    -0.09
    è¿Ľåº¦
    -0.09
    è§Ĩè§Ĵ
    -0.09
    çŀ§
    -0.08
    åķĥ
    -0.08
    æĢĨ
    -0.08
     peer
    -0.08
     Miy
    -0.08
    责任æĦŁ
    -0.08
    POSITIVE LOGITS
    è¯ŃéŁ³
    0.12
    å½ķéŁ³
    0.12
    Voice
    0.11
    _echo
    0.11
    Speech
    0.10
    åı£è¯Ń
    0.10
    èģĭ
    0.10
     Siri
    0.10
    æĻ®éĢļè¯Ŀ
    0.10
    åĵij
    0.10
    Activations Density 0.142%

    No Known Activations