© 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. 50979
    Prev
    Next
    INDEX
    Explanations

    leaving or ending something

    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
    追溯
    -0.09
    建çŃij设计
    -0.09
    èĿł
    -0.09
    马æĭīæĿ¾
    -0.09
    éĴ¹
    -0.09
    ifr
    -0.09
    漫
    -0.09
    owns
    -0.09
    _HAL
    -0.09
    头æĿ¡
    -0.09
    POSITIVE LOGITS
     pink
    0.09
    åĵºä¹³
    0.09
    æŃ¤äºº
    0.08
    UMP
    0.08
    atori
    0.08
     mortal
    0.07
    æĺİæĻº
    0.07
    æŃ¤é¡¹
    0.07
    çĶļ
    0.07
    éĥ¡
    0.07
    Activations Density 0.252%

    No Known Activations