© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62773
    Prev
    Next
    INDEX
    Explanations

    newsroom editor radio studio

    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
    代è¨Ģ
    -0.11
    ÑĢÑĥ
    -0.10
    解说
    -0.10
    å¹Į
    -0.10
    代è¨Ģ人
    -0.09
    Ñįм
    -0.09
    åı¹æģ¯
    -0.09
    åįķ车
    -0.09
    OAD
    -0.08
    第ä¸ĥ
    -0.08
    POSITIVE LOGITS
    ç¼ĸè¾ij
    0.10
    bing
    0.10
     edit
    0.10
    åĪ¶ä½ľ
    0.10
     staff
    0.10
    ding
    0.09
    (edit
    0.09
    è´Ŀå°Ķ
    0.09
    çģµæ´»
    0.09
     Studios
    0.09
    Activations Density 0.202%

    No Known Activations