© 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. 8911
    Prev
    Next
    INDEX
    Explanations

    have you tried

    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¨ä½ĵåijĺå·¥
    -0.10
    èĭįçĻ½
    -0.09
    åĿIJèIJ½äºİ
    -0.08
    åħħæ²Ľ
    -0.08
    ä½ĵæ£Ģ
    -0.08
     powerless
    -0.08
    åĥ
    -0.08
    ç½ħ
    -0.08
    åħ¨ç¨ĭ
    -0.08
     Fucking
    -0.08
    POSITIVE LOGITS
    çģµæĦŁ
    0.12
    æĬĢæ³ķ
    0.12
    æĪIJåĵģ
    0.12
    æĿIJæĸĻ
    0.11
     inspir
    0.10
    åĪĽä½ľ
    0.10
     изгоÑĤов
    0.10
    模çī¹
    0.10
    éĿ¢æĸĻ
    0.09
    loom
    0.09
    Activations Density 0.166%

    No Known Activations