© 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. 8724
    Prev
    Next
    INDEX
    Explanations

    chronicles, files, and scrolls

    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
    erville
    -0.08
    Invoker
    -0.08
    çļĦ身ä½ĵ
    -0.08
    éłĵ
    -0.08
    less
    -0.08
    çļĦæĥħ绪
    -0.08
    çļĦå±ĢéĿ¢
    -0.08
    åĬłåĢį
    -0.08
     зав
    -0.08
    stell
    -0.08
    POSITIVE LOGITS
    æ·¡
    0.10
    ä»İæĿ¥
    0.09
    è°ģèĥ½
    0.09
    èĽ¾
    0.09
    udes
    0.09
    Ùģار
    0.08
    èijµ
    0.08
    åķĨæľº
    0.08
    èĿ¶
    0.08
    uite
    0.08
    Activations Density 0.021%

    No Known Activations