© 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. 8420
    Prev
    Next
    INDEX
    Explanations

    listing items separately

    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
    iego
    -0.09
    4
    -0.09
    axes
    -0.09
    åģļå¾Ĺ
    -0.09
    5
    -0.08
    thon
    -0.08
    8
    -0.08
    ouch
    -0.08
    éĻĽ
    -0.08
    icity
    -0.08
    POSITIVE LOGITS
    åĬłä¹ĭ
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    oldt
    0.09
    综åIJĪæķ´æ²»
    0.09
    odus
    0.09
    å°±è¿ŀ
    0.09
    è¿Ļæīįæĺ¯
    0.09
    æĪij个人
    0.09
    åħ¶å®ĥ
    0.08
    æİĸ
    0.08
    Activations Density 0.138%

    No Known Activations