© 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. 53600
    Prev
    Next
    INDEX
    Explanations

    temporarily out of stock or on hiatus

    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
    æĽĻ
    -0.10
    åĵĨ
    -0.09
    EVER
    -0.09
    èĪľ
    -0.08
    åĵ¨
    -0.08
    婪
    -0.08
    丢
    -0.08
    ACT
    -0.08
    _mA
    -0.08
    VE
    -0.08
    POSITIVE LOGITS
    æļĤæŶ
    0.21
    æļĤ
    0.19
    æļ«
    0.19
     tạm
    0.14
     temporarily
    0.13
    ãģĹãģ°ãĤīãģı
    0.12
    ä¸Ģ段æŶéĹ´
    0.12
    æļĤåģľ
    0.11
     пока
    0.11
    缴åĪ°
    0.10
    Activations Density 0.049%

    No Known Activations