© 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. 35799
    Prev
    Next
    INDEX
    Explanations

    live in / attend classrooms

    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
    èĮ¬
    -0.08
    riv
    -0.08
    éĢIJä¸Ģ
    -0.08
    碴
    -0.08
    çĬĢ
    -0.08
    âĸ¹
    -0.08
     ÑĢей
    -0.08
    cheid
    -0.08
    è°ģéĥ½
    -0.07
    缶
    -0.07
    POSITIVE LOGITS
    åľ¨ä¸Ģ个
    0.17
    çļĦæĺ¯
    0.12
    éĤ£ç§į
    0.11
    ä»Ģä¹Īæł·çļĦ
    0.11
    ä¸Ģç§į
    0.11
    éģĩåĪ°äºĨ
    0.11
    äºĨä¸Ģ个
    0.10
    éĿ¢ä¸´çļĦ
    0.10
    åĵĪå°Ķ
    0.10
    æĪIJçĨŁçļĦ
    0.10
    Activations Density 0.398%

    No Known Activations