© 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. 27832
    Prev
    Next
    INDEX
    Explanations

    membrane transport and permeability

    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
    缨
    -0.11
    æ·¡å®ļ
    -0.11
    è¿©
    -0.10
    丧
    -0.10
    ä»İ容
    -0.10
    æŀķ头
    -0.09
    åľ¨è·¯ä¸Ĭ
    -0.09
    缩å°ı
    -0.09
    ä¸ĭåıij
    -0.09
    _OBJC
    -0.09
    POSITIVE LOGITS
    åħ¥
    0.10
     кÑĥда
    0.10
    æ¹ĺ
    0.10
    æ¸ĹéĢı
    0.09
    çĶľ
    0.08
    åIJ¸æĶ¶
    0.08
    éĢļéģĵ
    0.08
    ä¸ĵ
    0.08
    coc
    0.08
    æ¦ľ
    0.08
    Activations Density 0.441%

    No Known Activations