© 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. 10781
    Prev
    Next
    INDEX
    Explanations

    historical context

    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
    åī©
    -0.09
    èĩ³ä»Ĭ
    -0.08
    没è§ģè¿ĩ
    -0.08
    sworth
    -0.08
    ToEnd
    -0.08
    ä¸Ńéĥ¨
    -0.08
    亲人
    -0.08
    åĩ»
    -0.08
    çĭ¬å®¶
    -0.08
    ä¸Ģæĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    æĹ©åľ¨
    0.20
    åľ¨æѤä¹ĭåīį
    0.15
     prior
    0.14
    æĹ©å°±
    0.14
    æľĢæĹ©çļĦ
    0.13
    æľĢæĹ©
    0.13
     earlier
    0.13
    æĹ©å·²
    0.12
    æѤåīį
    0.12
    èIJĮ
    0.12
    Activations Density 0.170%

    No Known Activations