© 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. 49765
    Prev
    Next
    INDEX
    Explanations

    titles and positions

    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
    æŀIJ
    -0.09
    è¿ĺä¸į
    -0.09
    å«Ĥ
    -0.08
    gue
    -0.08
    éĢļåħ³
    -0.08
     паÑĢа
    -0.08
     Netherlands
    -0.08
    æ¸ĶèĪ¹
    -0.08
    æ¸Ķæ°ij
    -0.08
    éĺŁåijĺ们
    -0.08
    POSITIVE LOGITS
    å±Ģéķ¿
    0.17
    æł¡éķ¿
    0.16
    è´Łè´£äºº
    0.15
     trÆ°á»Łng
    0.14
    åħļå§Ķ书记
    0.14
     director
    0.13
    è¡Įéķ¿
    0.13
    éĥ¨éķ¿
    0.13
     president
    0.13
    director
    0.13
    Activations Density 0.220%

    No Known Activations