© 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. 9203
    Prev
    Next
    INDEX
    Explanations

    all-around

    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
    oret
    -0.08
    级
    -0.08
    屡
    -0.08
    CLS
    -0.08
    neh
    -0.08
    åĮºåĪĨ
    -0.08
    ogra
    -0.08
    -only
    -0.07
    çľ¨çľ¼
    -0.07
    ä¸ĬçĻ¾
    -0.07
    POSITIVE LOGITS
    èĮµ
    0.11
     ÑħоÑĢо
    0.10
    åı¯è§Ĥ
    0.10
    åĸľçĪ±
    0.10
    fare
    0.09
    åħ¨éĿ¢åıijå±ķ
    0.09
    ãĤĪãģĭãģ£ãģŁ
    0.09
    好çļĦ
    0.09
    ä¸įä½³
    0.09
    大éħĴåºĹ
    0.09
    Activations Density 0.006%

    No Known Activations