© 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. 50861
    Prev
    Next
    INDEX
    Explanations

    strategy and tactics

    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
    amar
    -0.10
    梢
    -0.08
    éĶĭ
    -0.08
    éļıæŶéļı
    -0.08
    å¸ĤåľºåĮĸ
    -0.08
    宫
    -0.08
    æģ¶åĮĸ
    -0.08
    rong
    -0.08
    éľĦ
    -0.08
    顶å±Ĥ设计
    -0.08
    POSITIVE LOGITS
    orte
    0.09
    åĿ
    0.09
    æĻº
    0.09
    åľ°ä½į
    0.09
    orta
    0.08
    çĵľ
    0.08
    赡
    0.08
    ç¥ĸåĽ½
    0.08
    еннаÑı
    0.08
     Mant
    0.08
    Activations Density 0.026%

    No Known Activations