© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    when questions

    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
    å½ĵæŶçļĦ
    -0.09
    èµ°ä¸ĭåİ»
    -0.09
    hip
    -0.09
    æī¾åĩº
    -0.09
    ç¥ŀä»Ļ
    -0.09
    æijĬ
    -0.09
    å½ĵæŶ
    -0.09
    éķĮ
    -0.08
    足足
    -0.08
    otto
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹ĪæŶåĢĻ
    0.12
    æŶåĢĻ
    0.10
    å¹´å¼Ģå§ĭ
    0.09
    ä½ķæŶ
    0.09
    è§ģè¿ĩ
    0.08
    Verb
    0.08
    åĴĦ
    0.08
    èIJĭ
    0.08
     Winds
    0.08
    æŃ¢
    0.08
    Activations Density 0.026%

    No Known Activations