© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7813
    Prev
    Next
    INDEX
    Explanations

    direction or state changes

    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
    åĮĸçļĦ
    -0.12
    éªĭ
    -0.10
    fully
    -0.10
    ened
    -0.10
    uite
    -0.09
    åĮĸè¿Ľç¨ĭ
    -0.09
    éIJĺ
    -0.09
    аÑĩ
    -0.09
    ä¾Ľç»Ļ
    -0.09
    izers
    -0.08
    POSITIVE LOGITS
    /from
    0.09
    gether
    0.09
    /down
    0.09
    å¤©åºľ
    0.09
    sWith
    0.09
    æĥľ
    0.09
    ä¸ĵåĮº
    0.09
    缨
    0.09
    亲åıĭ
    0.09
    å±ĢéĿ¢
    0.08
    Activations Density 0.088%

    No Known Activations