© 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. 49767
    Prev
    Next
    INDEX
    Explanations

    preferences and desires

    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
    å±¥
    -0.09
    ä¸įåĨį
    -0.09
    éĨª
    -0.09
    uant
    -0.09
    NES
    -0.08
    ä»İæѤ
    -0.08
    åĢ¼å¾Ĺä¸Ģ
    -0.08
    CG
    -0.08
    çļĦåľ°åĽ¾
    -0.08
    æ»ĭ
    -0.08
    POSITIVE LOGITS
    çļĦçIJĨæĥ³
    0.16
    çIJĨæĥ³
    0.16
    çIJĨæĥ³çļĦ
    0.15
    æĹłå¥Ī
    0.14
    åı¯æĥľ
    0.12
     ideal
    0.12
    éģĹæĨ¾
    0.12
    å¾Īæĥ³
    0.12
    ä½ĨçĶ±äºİ
    0.11
    滹
    0.11
    Activations Density 0.071%

    No Known Activations