© 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. 37093
    Prev
    Next
    INDEX
    Explanations

    links and connections

    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
     Jacqu
    -0.09
    åĴĢ
    -0.09
    éĥģéĹ·
    -0.08
    èĢ³æľµ
    -0.08
    äºĨæĪijçļĦ
    -0.08
    éĿ¢åŃĶ
    -0.08
    æģ£
    -0.08
    èĢ³
    -0.08
    DirectoryName
    -0.08
    亡
    -0.08
    POSITIVE LOGITS
     ties
    0.16
    纽带
    0.12
     connection
    0.12
     relation
    0.12
    åħ³ç³»
    0.12
     Connection
    0.11
    åħ³èģĶ
    0.11
     connections
    0.11
    èģĶç³»
    0.11
    connection
    0.11
    Activations Density 0.042%

    No Known Activations