© 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. 37011
    Prev
    Next
    INDEX
    Explanations

    a harmful, fault, variety, workshop, lack

    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
    .tel
    -0.10
    éĵİ
    -0.09
    idal
    -0.09
    æģ¢
    -0.08
    egan
    -0.08
    aho
    -0.08
    æĸ°ä¸ĸ纪
    -0.08
    ãģĹãģ°
    -0.08
    ÑĢÑıд
    -0.08
    rah
    -0.08
    POSITIVE LOGITS
    åıijè´¢
    0.09
    æİ´
    0.09
     пÑĢоÑģ
    0.09
    èİ·å¾ĹæĦŁ
    0.09
    çªģåıijäºĭ件
    0.09
    vard
    0.08
    å½ĵåīį
    0.08
    ä¸Ģä½į
    0.08
    (concat
    0.08
    äºŃ
    0.08
    Activations Density 0.275%

    No Known Activations