© 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. 56301
    Prev
    Next
    INDEX
    Explanations

    rate of

    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
    欢è¿İæĤ¨
    -0.09
    çĶ³
    -0.09
    åľºåIJĪ
    -0.09
    ÙĦاÙħ
    -0.09
    åĩ¡æľ¬ç½ij
    -0.08
    åı£æ°Ķ
    -0.08
    gone
    -0.08
    arb
    -0.08
    ä½İæĪIJæľ¬
    -0.08
    è¿Ļ对äºİ
    -0.08
    POSITIVE LOGITS
    åĪĨåĪ«ä¸º
    0.13
    大æ¦Ĥæĺ¯
    0.13
    æĺ¯å¤ļå°ij
    0.12
    约为
    0.12
    é«ĺè¾¾
    0.11
    çĪ²
    0.11
    å¤ļå°ij
    0.11
    使çĶ¨ç¶²è·¯
    0.10
    ä¸Ģåıªæīĭ
    0.10
    ä¸įä½İäºİ
    0.10
    Activations Density 0.369%

    No Known Activations