© 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. 8819
    Prev
    Next
    INDEX
    Explanations

    central element or focal point

    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
    ëŀŃ
    -0.10
    ilver
    -0.09
    >xpath
    -0.09
    æķ¬è¯·
    -0.09
    尽头
    -0.09
    artz
    -0.08
    icken
    -0.08
    éĤ£è¾¹
    -0.08
    ëŀĻ
    -0.08
    éĢĤåºĶ
    -0.08
    POSITIVE LOGITS
    ä¸ºæł¸å¿ĥ
    0.12
    贯穿
    0.12
     centerpiece
    0.11
    带åĬ¨
    0.10
    èµ·åĪ°
    0.10
    æł¸å¿ĥ
    0.10
    =center
    0.10
     role
    0.10
    æŀ¢çº½
    0.10
    为ä¸Ńå¿ĥ
    0.10
    Activations Density 0.149%

    No Known Activations