© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51876
    Prev
    Next
    INDEX
    Explanations

    lack of flavor or color

    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
    ideo
    -0.09
    witch
    -0.08
    顺åĬ¿
    -0.08
    ance
    -0.08
    æĶ¹å»º
    -0.08
    误
    -0.08
    踪
    -0.08
    åħ¬å¼Ģåıij
    -0.08
    ExecutionContext
    -0.08
    wnd
    -0.08
    POSITIVE LOGITS
     Midi
    0.12
    çĺª
    0.11
    表æĥħ
    0.11
    é¼ĵ
    0.11
    edback
    0.11
    å¤ļ彩
    0.10
    丰å¯Į
    0.10
    寡
    0.10
    丰å¯ĮçļĦ
    0.10
    _COLORS
    0.10
    Activations Density 0.049%

    No Known Activations