© 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. 26783
    Prev
    Next
    INDEX
    Explanations

    bringing in

    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
    åĩºåĽ½
    -0.11
    çļĦè¿ĽæŃ¥
    -0.10
    æ´¾åĩº
    -0.10
    åľ¨ç½ijä¸Ĭ
    -0.10
    æĹ¶è¾°
    -0.09
    æĶ¾è¿ĩ
    -0.09
    åľ¨ä»ĸ
    -0.09
    ä»ĺ
    -0.09
    Outlet
    -0.09
    åĩºéŨ
    -0.09
    POSITIVE LOGITS
    /out
    0.09
    å¤ĸæı´
    0.09
    äºĨä¸Ģæī¹
    0.09
    ég
    0.08
    Ùħد
    0.08
    lec
    0.08
    gers
    0.08
    æĸ°çļĦä¸Ģ
    0.08
    åĨįå¤ļ
    0.08
    nung
    0.08
    Activations Density 0.007%

    No Known Activations