© 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. 51964
    Prev
    Next
    INDEX
    Explanations

    animals, lodges,

    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
    åŁ
    -0.09
    rat
    -0.09
    æݥ管
    -0.09
    ÙĤات
    -0.09
    ä¸ĭ鼨
    -0.09
    æĬ±çĿĢ
    -0.09
     Rat
    -0.09
    æĸ¯åŁº
    -0.09
    åĻ
    -0.09
    ilde
    -0.09
    POSITIVE LOGITS
    å§Ķ书记
    0.08
    chs
    0.08
    ence
    0.08
    é¢Ħ计
    0.07
    éļı
    0.07
    è§
    0.07
    ion
    0.07
    во
    0.07
    çľī
    0.07
    åħ¨èº«
    0.07
    Activations Density 0.017%

    No Known Activations