© 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. 3833
    Prev
    Next
    INDEX
    Explanations

    control and possession

    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
    ä½ĵåĪ¶æĶ¹éĿ©
    -0.10
    è§īå¾Ĺèĩªå·±
    -0.10
    èĺ¸
    -0.09
    飧æĢ§
    -0.09
    æīĥ
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
    åĨı
    -0.09
    åľ¨äº¬
    -0.08
    _FAST
    -0.08
    _ATTRIB
    -0.08
    POSITIVE LOGITS
    大éĥ¨åĪĨ
    0.12
    ç»Ŀ大éĥ¨åĪĨ
    0.10
    大çīĩ
    0.10
     вÑģÑİ
    0.09
     entire
    0.09
    åĺĺ
    0.09
    ä¸ĢåįĬ
    0.08
    è¯łéĩĬ
    0.08
     Alma
    0.08
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.08
    Activations Density 0.063%

    No Known Activations