© 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. 28020
    Prev
    Next
    INDEX
    Explanations

    of [locations or titles]

    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
    çıŃ主任
    -0.10
    ä¿£
    -0.09
    æį¶
    -0.09
    باب
    -0.09
    å¯ĵæĦı
    -0.09
    çļĦæĸĩåŃĹ
    -0.09
    ToPoint
    -0.08
    åĨįçĶŁ
    -0.08
    _PUT
    -0.08
    PTR
    -0.08
    POSITIVE LOGITS
    为代表çļĦ
    0.10
    é²ľ
    0.09
    UB
    0.09
    é¦ĸåıij
    0.09
    è°¤
    0.08
    åŁİéĩĮ
    0.08
    å½¼
    0.08
    è°ļ
    0.08
    irs
    0.08
     INS
    0.08
    Activations Density 0.052%

    No Known Activations