© 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. 52403
    Prev
    Next
    INDEX
    Explanations

    church names and types

    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
    çĸ²
    -0.11
    ä¸ĢåĪ»
    -0.10
    è¿Ļä¸Ģå¹´
    -0.09
    åĨ»
    -0.09
    çįIJ
    -0.09
    ä¸į便
    -0.09
    usic
    -0.09
    æ¾Į
    -0.09
    çĪ±ä¸Ĭ
    -0.09
    è´Łèį·
    -0.09
    POSITIVE LOGITS
    çĽ¸ä¿¡
    0.09
    çĤĶ
    0.08
    еÑĢÑĤ
    0.08
    éľĪ
    0.08
    ä¸įçĶ¨
    0.08
     HO
    0.08
    æŦ
    0.08
    UDO
    0.08
    chten
    0.08
    æ»´
    0.07
    Activations Density 0.101%

    No Known Activations