© 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. 62505
    Prev
    Next
    INDEX
    Explanations

    over ____ half

    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
    æ´¾åĩº
    -0.09
    éķ¶
    -0.09
    ase
    -0.09
    arus
    -0.08
    ilded
    -0.08
    çĶŁäº§æĢ»åĢ¼
    -0.08
    åİļ度
    -0.08
    çł´æįŁ
    -0.08
    ther
    -0.08
    æľŁåĨħ
    -0.08
    POSITIVE LOGITS
    ä¸ĬçĻ¾
    0.09
    iner
    0.09
    éĢ¾
    0.09
    äºĨä»ĸçļĦ
    0.08
    æ¸ħé¦Ļ
    0.08
     Ñĩем
    0.08
    黼
    0.08
    ifter
    0.08
    æĥ³æ³ķ
    0.08
    è¿Ļæĺ¯ä¸Ģç§į
    0.08
    Activations Density 0.004%

    No Known Activations