© 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. 10103
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    éĴµ
    -0.10
    isty
    -0.08
    åĬ¡
    -0.08
    ä¾ĿéĿł
    -0.08
     phẩm
    -0.08
    åĩŃçĿĢ
    -0.08
    æ»´æ»´
    -0.08
    rom
    -0.08
    çİ«
    -0.08
    ç¢į
    -0.08
    POSITIVE LOGITS
    goal
    0.09
    -<?
    0.09
    pur
    0.09
    èIJ¥ä¸ļ
    0.09
    髦
    0.08
    éĩįè¦ģä½ľçĶ¨
    0.08
    ä»ħ代表
    0.08
    /includes
    0.08
    æĬĵ好
    0.08
    çĪª
    0.08
    Activations Density 0.030%

    No Known Activations