© 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. 36126
    Prev
    Next
    INDEX
    Explanations

    lead or helped lead

    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
    伸
    -0.10
     Opr
    -0.09
    rum
    -0.08
    åī¯ç§ĺ书éķ¿
    -0.08
     crow
    -0.08
    å±Ĭ
    -0.08
     Stre
    -0.08
    angling
    -0.08
    她说
    -0.08
    èĮħ
    -0.08
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.12
    łéĻ¤
    0.10
    æŶéļĶ
    0.10
    带é¢Ĩ
    0.10
    çĭİ
    0.09
    .Conn
    0.09
    oit
    0.09
    dera
    0.09
    æĭĸ
    0.09
    æĦı大
    0.09
    Activations Density 0.033%

    No Known Activations