© 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. 58337
    Prev
    Next
    INDEX
    Explanations

    look straight ahead

    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
    æĺķ
    -0.09
    è½½
    -0.09
    设计
    -0.09
    åħ¬çĦ¶
    -0.08
    ç«ŀ
    -0.08
    åī¥
    -0.08
    åIJĮä¸ļ
    -0.08
    IZER
    -0.08
    æĸĻ
    -0.08
     designs
    -0.08
    POSITIVE LOGITS
    çĨŁç»ĥ
    0.11
    åĪ°ä½į
    0.11
    ç´§çĽ¯
    0.11
    è¿İ
    0.10
    æĦıè¯Ĩ
    0.10
    å¯Įæ°ij
    0.10
    åĿĩåĮĢ
    0.10
    åľ¨äº¬
    0.09
    äºĭåıij
    0.09
    主åĬ¨æĢ§
    0.09
    Activations Density 0.092%

    No Known Activations