© 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. 8200
    Prev
    Next
    INDEX
    Explanations

    content rating or advisory

    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
    åħ´èĩ´
    -0.11
    åľ¨åºĬä¸Ĭ
    -0.10
    æĢİä¹ĪåĬŀ
    -0.09
    usk
    -0.09
    amm
    -0.09
    жи
    -0.08
    cup
    -0.08
    ipt
    -0.08
    Powered
    -0.08
    é¥Ń
    -0.08
    POSITIVE LOGITS
    åĽłä¸ºå®ĥ
    0.10
    å®ŀè·µä¸Ń
    0.09
    itas
    0.09
    è§īæĤŁ
    0.08
    åĴĮæĬĢæľ¯
    0.08
     Ñģли
    0.08
    MBER
    0.08
    tti
    0.08
    ë§
    0.08
    æ°´éĿ¢
    0.08
    Activations Density 0.007%

    No Known Activations