© 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. 4970
    Prev
    Next
    INDEX
    Explanations

    follow up

    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
    аÑĪ
    -0.09
    åĩºåħ¥å¢ĥ
    -0.09
    ople
    -0.09
    æ¯ıéĢ¢
    -0.09
    éĢłèĪ¹
    -0.09
    è¿Ļæł·æīįèĥ½
    -0.09
    æ¦Ĥæĭ¬
    -0.09
    ä¸ĢæŶ
    -0.09
    èµ°åĩº
    -0.09
    æłijæľ¨
    -0.09
    POSITIVE LOGITS
    è·Łè¿Ľ
    0.13
    追
    0.11
    追寻
    0.10
    追究
    0.09
    è·Łè¸ª
    0.09
     har
    0.08
    追踪
    0.08
     дейÑģÑĤвие
    0.08
    èIJ½å®ŀ
    0.08
    å·¥ä½ľä¸Ń
    0.08
    Activations Density 0.016%

    No Known Activations