© 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. 48945
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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
    ãģĿãģ®ä»ĸ
    -0.11
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
     기íĥĢ
    -0.09
    åįģäºĮäºĶ
    -0.09
    Êķ
    -0.08
    éĢ¡
    -0.08
    æѤæĸĩ
    -0.08
    âŀ»
    -0.07
     Parkway
    -0.07
    åĹ³
    -0.07
    POSITIVE LOGITS
    aker
    0.11
    erate
    0.09
    ização
    0.09
    ally
    0.09
     vra
    0.08
    ä¸ĢéĿ¢
    0.08
    髹
    0.08
    æºIJæºIJ
    0.08
    å½ĵæŶçļĦ
    0.08
    ä»ĸ认为
    0.08
    Activations Density 2.235%

    No Known Activations