© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6706
    Prev
    Next
    INDEX
    Explanations

    back and forth

    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
    ä¹Łåıªèĥ½
    -0.12
    为广大
    -0.11
    ä¸įæĸ¹ä¾¿
    -0.10
     Convenient
    -0.09
    åľ¨å½ĵåľ°
    -0.09
    侥幸
    -0.09
    è¾ĩ
    -0.09
    ibus
    -0.09
    鹦
    -0.09
    ä¾¥
    -0.08
    POSITIVE LOGITS
    variants
    0.08
    æīĺ
    0.08
    Partition
    0.08
    lesh
    0.08
    /out
    0.08
    æ·ij
    0.08
    ä¸įäºĨ
    0.08
    æ°ĵ
    0.08
    åĩłæ¬¡
    0.08
    ç¨ļ
    0.08
    Activations Density 0.014%

    No Known Activations