© 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. 55537
    Prev
    Next
    INDEX
    Explanations

    relative clauses

    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
    æĻĮ
    -0.10
    ä¸ij
    -0.09
    æĭľ
    -0.09
    çĶŁäº§çĶŁæ´»
    -0.09
    ç£ķ
    -0.09
    æłĩå¿ĹæĢ§
    -0.09
    nable
    -0.09
    åľ¨å®¶
    -0.09
    å¼ŁåŃIJ
    -0.09
    룴
    -0.09
    POSITIVE LOGITS
    æĹ¢è¦ģ
    0.08
    溢价
    0.08
    _NE
    0.08
    gü
    0.08
    PlainText
    0.08
    æ´»ä¸ĭåİ»
    0.08
    åĨ²
    0.08
    ä½łè¿ĺ
    0.08
    è¶Ĭæĺ¯
    0.08
    LOPT
    0.07
    Activations Density 0.153%

    No Known Activations