© 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. 6340
    Prev
    Next
    INDEX
    Explanations

    game progression and ability points

    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
    æŃ£åľ¨è¿Ľè¡Į
    -0.10
    alone
    -0.09
    æĬ¢æĬĵ
    -0.09
    åı¯èĥ½åıijçĶŁ
    -0.09
    å®£ä¼ł
    -0.09
    owo
    -0.08
    mic
    -0.08
    åįķ车
    -0.08
    宣æī¬
    -0.08
    åıijæĮ¥
    -0.08
    POSITIVE LOGITS
    çĻĸ
    0.11
    æıIJåįĩ
    0.10
    è·Ľ
    0.10
    æĭĦ
    0.09
    éĢł
    0.09
    骡
    0.09
    æį¢æĿ¥
    0.09
    ored
    0.08
    ä¸Ģåij¨
    0.08
    è§£éĶģ
    0.08
    Activations Density 0.038%

    No Known Activations