© 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. 3944
    Prev
    Next
    INDEX
    Explanations

    Bureau of Statistics estimates

    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
    æĹ¶ä»£çļĦ
    -0.10
    ä¸įæĪIJ
    -0.10
    æıĸ
    -0.09
    åĢĻéĢī
    -0.09
    éĺĢ
    -0.09
    奥
    -0.08
    .innerHeight
    -0.08
    çķĮçļĦ
    -0.08
    CallCheck
    -0.08
    iore
    -0.08
    POSITIVE LOGITS
    大å®Ĺ
    0.11
    è·ŁæĪij
    0.09
    éĹ²ç½®
    0.09
    ä¸ĵ
    0.08
     Fel
    0.08
    5
    0.08
    ¼
    0.08
     Lor
    0.08
    æķ°æį®æĺ¾ç¤º
    0.08
    lex
    0.08
    Activations Density 0.033%

    No Known Activations