© 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. 55015
    Prev
    Next
    INDEX
    Explanations

    understanding mechanisms of processes

    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
    æĦıä¹īä¸ĬçļĦ
    -0.10
    æĦıä¹īä¸Ĭ
    -0.08
    azio
    -0.07
    èĢĥéĩı
    -0.07
     consideration
    -0.07
    å¾Ī强
    -0.07
    ita
    -0.07
    为ä¹ĭ
    -0.07
    Visible
    -0.07
     publicly
    -0.07
    POSITIVE LOGITS
    åĪ°åºķæĺ¯
    0.12
    究竣æĺ¯
    0.12
    å¤įæĿĤçļĦ
    0.11
    éļıçĿĢæŶéĹ´
    0.11
    ibern
    0.11
    ãģ©ãģ®ãĤĪãģĨãģ«
    0.10
    æ²¾
    0.10
    纷
    0.10
    ouver
    0.10
    åĹ
    0.10
    Activations Density 0.637%

    No Known Activations