© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21825
    Prev
    Next
    INDEX
    Explanations

    RNA interference and small RNAs

    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
    ä»ħ代表
    -0.10
    elper
    -0.09
    erner
    -0.09
    æīĢæıIJä¾Ľ
    -0.09
    éªĩ
    -0.08
     sdk
    -0.08
    æĦŁäºº
    -0.08
    ä¼ĺæĥłæĶ¿çŃĸ
    -0.08
    éĶ®çĽĺ
    -0.08
    normalized
    -0.08
    POSITIVE LOGITS
    èį¤
    0.09
    trl
    0.09
    æ¼¾
    0.09
    çļİ
    0.08
    лÑĥ
    0.08
    æŀIJ
    0.08
    æĬĺåıł
    0.08
    èıŁ
    0.08
    -fold
    0.08
    _BACKGROUND
    0.08
    Activations Density 0.385%

    No Known Activations