© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9800
    Prev
    Next
    INDEX
    Explanations

    range or duration limits

    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
    Coder
    -0.08
    çľļ
    -0.08
     TCL
    -0.08
    acute
    -0.08
    OURS
    -0.08
    å¤Ń
    -0.08
    颤
    -0.08
    æ½ĩæ´Ĵ
    -0.08
    åıĺçİ°
    -0.07
    wel
    -0.07
    POSITIVE LOGITS
    ä¹ł
    0.09
    æĢ»ç»ĵ
    0.09
    æĬķèµĦé¢Ŀ
    0.09
    iband
    0.09
    ç¢
    0.08
    滾
    0.08
    ç»Ļèĩªå·±
    0.08
    ä¸ĢéŨ
    0.08
    åĬªåĬĽ
    0.08
    楦
    0.08
    Activations Density 0.081%

    No Known Activations