© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12067
    Prev
    Next
    INDEX
    Explanations

    container and quantity

    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
    athing
    -0.10
    å³°ä¼ļ
    -0.09
    ofday
    -0.09
    dap
    -0.09
    æ¯ı天éĥ½
    -0.09
    äºĮçĻ¾
    -0.09
    мо
    -0.08
    ä¸ĢæĬ¹
    -0.08
    åıĮèħ¿
    -0.08
    igans
    -0.08
    POSITIVE LOGITS
    หาร
    0.09
    æĶ¹éĿ©åĪĽæĸ°
    0.08
    æ·±åĮĸ
    0.08
    æĭĨ
    0.08
    ·»
    0.08
    寻
    0.08
    reuse
    0.08
    æĤŃ
    0.07
    主è¦ģä»İäºĭ
    0.07
    _VC
    0.07
    Activations Density 0.003%

    No Known Activations