© 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. 63080
    Prev
    Next
    INDEX
    Explanations

    timber, wood, meat, silk, valuable species

    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
    éĢŀ
    -0.09
    èĽĢ
    -0.09
    Ø·ÙĪ
    -0.08
    çģ°å°ĺ
    -0.08
     Brett
    -0.08
    æĪIJåĬŁçļĦ
    -0.08
    éľī
    -0.08
    _FAIL
    -0.08
     ÑĥпÑĢав
    -0.08
    æĭĪ
    -0.08
    POSITIVE LOGITS
    ä¸ºçĽ®çļĦ
    0.09
    ä¾
    0.09
    éĵł
    0.09
    å¼ĢåıijåĪ©çĶ¨
    0.09
    èĤī
    0.09
    çĶľçĶľ
    0.09
    ä»·åĢ¼
    0.09
    ParallelGroup
    0.09
    ç»ıæµİæķĪçĽĬ
    0.09
    ä¾Ľ
    0.09
    Activations Density 0.137%

    No Known Activations