© 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. 49585
    Prev
    Next
    INDEX
    Explanations

    already completed or in progress

    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
    空åīį
    -0.11
    认è¯Ĩ
    -0.10
    åĿĬ
    -0.08
    åĽŀæĶ¶
    -0.08
    ủng
    -0.08
    .addTab
    -0.08
    æī¾åĽŀ
    -0.08
    _missing
    -0.08
    ä¼ı
    -0.08
    ä¸į失
    -0.08
    POSITIVE LOGITS
     already
    0.20
    å·²ç»ıå¼Ģå§ĭ
    0.19
    already
    0.18
    å·²ç»ı
    0.18
    å·²ç¶ĵ
    0.17
     Ñĥже
    0.17
     Already
    0.16
    å·²å®ĮæĪIJ
    0.16
    Already
    0.16
    ãģĻãģ§ãģ«
    0.16
    Activations Density 0.098%

    No Known Activations