© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36795
    Prev
    Next
    INDEX
    Explanations

    stretch and shrink

    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
     Transparent
    -0.09
    -transparent
    -0.09
     barg
    -0.09
    _projection
    -0.09
    izontal
    -0.09
    /desktop
    -0.09
    å°±çŁ¥éģĵ
    -0.09
    éĻĮçĶŁäºº
    -0.09
    æİĢ
    -0.08
     transparent
    -0.08
    POSITIVE LOGITS
    éĢĤ度
    0.11
    æĤ¦
    0.09
    ä¸Ī
    0.09
    iqu
    0.09
    éĢĤåºĶ
    0.08
    able
    0.08
    笼
    0.08
    Blur
    0.08
     Infinite
    0.08
    æĺŃ
    0.08
    Activations Density 0.013%

    No Known Activations