© 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. 61211
    Prev
    Next
    INDEX
    Explanations

    forms of "to be" followed by diverse descriptors

    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
    è¿ĺè®°å¾Ĺ
    -0.10
    ç´¯äºĨ
    -0.10
    亵
    -0.10
    è¿ĻåĿĹ
    -0.10
    æĪijè¿ĺ
    -0.10
    AdapterFactory
    -0.09
    西路
    -0.09
    èĨĽ
    -0.09
    绥
    -0.08
    chg
    -0.08
    POSITIVE LOGITS
    çĶ¨æĿ¥
    0.10
    æĺ¯ä½ł
    0.09
    å¶
    0.09
     disb
    0.09
    æĺ¯åĽłä¸º
    0.08
    éĢģå¾Ģ
    0.08
    Sharing
    0.08
     part
    0.08
    éĢģåĪ°
    0.08
    åij½åIJį为
    0.08
    Activations Density 0.481%

    No Known Activations