© 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. 62256
    Prev
    Next
    INDEX
    Explanations

    best, most, largest

    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
    éĢ¢
    -0.10
    鼶è·Ŀ离
    -0.09
    -inner
    -0.09
    èĢħãģĮ
    -0.09
    æľīèĥ½åĬĽ
    -0.09
    æľīå¤ļä¹Ī
    -0.09
    åĸĦäºİ
    -0.09
    ç´Ģ
    -0.09
    ä½Ł
    -0.08
     Sole
    -0.08
    POSITIVE LOGITS
    æīĵåĩ»
    0.09
    ÑĢÑĥÑģ
    0.08
    ç¿»è¯ij
    0.08
    èĪģ
    0.08
     mods
    0.08
    åĨĽéĺŁ
    0.08
    å½Ģ
    0.08
    Mods
    0.08
     Brewer
    0.08
    _DX
    0.08
    Activations Density 0.013%

    No Known Activations