© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 48160
    Prev
    Next
    INDEX
    Explanations

    requirement or necessity

    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
    骨头
    -0.10
    ä»ĸèĩªå·±
    -0.09
    åĶĨ
    -0.09
    dsp
    -0.09
    æīĢéľĢè¦ģçļĦ
    -0.08
    éħ¥
    -0.08
    èĤĽ
    -0.08
    æīĢéľĢè¦ģ
    -0.08
    åĩĨå¤ĩå·¥ä½ľ
    -0.08
    ).__
    -0.08
    POSITIVE LOGITS
    大å¤ļæķ°
    0.10
    è¿ĻæĶ¯
    0.09
     Majority
    0.09
    ç»Ŀ大å¤ļæķ°
    0.09
    ä¸Ķ
    0.08
    èĬĤ课
    0.08
     meisten
    0.08
    夸
    0.08
    竳
    0.08
     indirect
    0.08
    Activations Density 0.023%

    No Known Activations