© 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. 35274
    Prev
    Next
    INDEX
    Explanations

    maybe or sometimes

    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
    è¾ĩ
    -0.10
    åĻ¤
    -0.09
    è´¬åĢ¼
    -0.08
    èĭ±æīį
    -0.08
    æĬµè¾¾
    -0.08
    achu
    -0.08
    åĨįä¹Ł
    -0.08
    ding
    -0.08
    驸
    -0.08
    OrNull
    -0.08
    POSITIVE LOGITS
    æݨ广åºĶçĶ¨
    0.12
    æ´¾åĩº
    0.09
    纶
    0.09
    æĺ¯ä¸Ģ款
    0.09
    祥
    0.08
     меÑģÑĤ
    0.08
    nod
    0.08
    æĺ¯ä¸Ģ家
    0.08
    ä¸īåĽ½
    0.08
    Initialization
    0.08
    Activations Density 0.210%

    No Known Activations