© 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. 2153
    Prev
    Next
    INDEX
    Explanations

    Azure Service endpoints

    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
    带åĪ°
    -0.09
    æĵĺ
    -0.09
    è°ĥ
    -0.08
    ondo
    -0.08
     Einstein
    -0.08
    èµĸ以
    -0.08
     rad
    -0.08
    ç¼Ĩ
    -0.08
    ç¥ł
    -0.08
     integ
    -0.08
    POSITIVE LOGITS
     Orr
    0.09
    æķĻä½ł
    0.09
     burge
    0.09
    èıĬ
    0.09
     Zuk
    0.08
    秣èµģ
    0.08
    ä¸ºçĽ®çļĦ
    0.08
    ç½ĺ
    0.08
     Via
    0.08
    éĢıè¿ĩ
    0.08
    Activations Density 0.129%

    No Known Activations