© 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. 30770
    Prev
    Next
    INDEX
    Explanations

    audio drivers and speakers

    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
    ä¸Ģçīĩ
    -0.10
    å¼Ĥ
    -0.10
    lei
    -0.09
    æīĭç»Ńè´¹
    -0.09
    ä¸Ģ身
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.09
    avra
    -0.08
    éľģ
    -0.08
    åĪ®
    -0.08
    äºĭ项
    -0.08
    POSITIVE LOGITS
    (tol
    0.09
    èĮĨ
    0.09
    讲è¯Ŀ
    0.09
    umann
    0.09
    esa
    0.09
    å¢Ļä¸Ĭ
    0.09
    iddleware
    0.08
    rb
    0.08
    _dtype
    0.08
    Listening
    0.08
    Activations Density 0.040%

    No Known Activations