© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions

    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
    åľ¨å¤ĸ
    -0.08
     Ecc
    -0.08
    æĶ¾å°Ħ
    -0.08
    ARING
    -0.08
    æķı
    -0.08
    è¾Ħ
    -0.08
     Ing
    -0.08
    FACT
    -0.08
     ecc
    -0.07
     hum
    -0.07
    POSITIVE LOGITS
    缸è§ģ
    0.10
    æīĵ交éģĵ
    0.10
    éĺħ读åħ¨æĸĩ
    0.10
    对å¾ħ
    0.10
    çĽ²
    0.10
    æľĢåħ³éĶ®
    0.09
    æļĮ
    0.09
    ç¥ĸåĽ½
    0.09
     pact
    0.09
    æĪĺèĥľ
    0.09
    Activations Density 0.093%

    No Known Activations