© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21387
    Prev
    Next
    INDEX
    Explanations

    pronunciation guides

    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
    åĪ¸
    -0.08
    _ub
    -0.08
     HÆ°Æ¡ng
    -0.08
    èµ°åĩº
    -0.08
    zz
    -0.08
    ury
    -0.08
     Abe
    -0.08
    ãģ½
    -0.08
    åıĭæĥħ
    -0.07
    Ä°YE
    -0.07
    POSITIVE LOGITS
    æ·Ĩ
    0.09
    èįŁ
    0.09
    å¿ĸ
    0.09
    NST
    0.09
    ç¨Ķ
    0.09
    çļĦ姿æĢģ
    0.09
    çĶ¨è½¦
    0.08
    æĥ®
    0.08
    åŀ©
    0.08
    æĺİæĺŁ
    0.08
    Activations Density 0.043%

    No Known Activations