© 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. 58587
    Prev
    Next
    INDEX
    Explanations

    working conditions

    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·Ħ
    -0.10
    å·¥ä½ľæľºåζ
    -0.10
    utherland
    -0.09
    åIJ¸åıĸ
    -0.09
    åIJ¸
    -0.09
    æĪ·ç±į
    -0.09
    ç¢İçīĩ
    -0.09
    æ¯ķä¸ļ
    -0.09
    妹
    -0.09
    èģĺç͍
    -0.09
    POSITIVE LOGITS
    bee
    0.09
    nehmer
    0.09
    åİĤæĪ¿
    0.08
    åľºä¸Ĭ
    0.08
    aho
    0.08
    èĢħçļĦ
    0.08
    нак
    0.08
    çĥŁèĬ±çĪĨ竹
    0.07
    çݯå¢ĥåį«çĶŁ
    0.07
    å¹¶åıij
    0.07
    Activations Density 0.074%

    No Known Activations