© 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. 30443
    Prev
    Next
    INDEX
    Explanations

    stating existence or characteristics

    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
    ä¸ĢçĶŁ
    -0.10
    èį¦
    -0.10
    ç»Ļå®Ŀå®Ŀ
    -0.09
    éĻ
    -0.09
    INGS
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    人士
    -0.08
    /Grid
    -0.08
    袱
    -0.08
    æĹłå½¢
    -0.08
    POSITIVE LOGITS
    åIJİèĢħ
    0.12
    æŀľæĸŃ
    0.09
    ä¸įæŃ¢
    0.09
    å°±è¶Ĭ
    0.09
    ä½ľèĢħæľ¬äºº
    0.09
     Shack
    0.08
    culate
    0.08
    åīįèĢħ
    0.08
    åĪ¶æŃ¢
    0.08
    æŁIJ个
    0.08
    Activations Density 0.216%

    No Known Activations