© 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. 31725
    Prev
    Next
    INDEX
    Explanations

    right side

    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·²ä¹ħçļĦ
    -0.11
    åĮĹè·¯
    -0.10
    å·²ä¹ħ
    -0.10
    ç¼
    -0.09
    ãģ£ãģ¨
    -0.09
    人æ°Ķ
    -0.09
     Crew
    -0.09
    ivor
    -0.09
    ÑĢенд
    -0.08
    ãĥ¬ãĥ¼
    -0.08
    POSITIVE LOGITS
    /left
    0.13
    /right
    0.11
    -hand
    0.09
    翼
    0.09
    DI
    0.09
    åĸĢ
    0.09
    å·¥ä¸ļä¼ģä¸ļ
    0.09
    干线
    0.08
    æ¬
    0.08
     dripping
    0.08
    Activations Density 0.110%

    No Known Activations