© 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. 51730
    Prev
    Next
    INDEX
    Explanations

    art and crafts

    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
    éĴ¹
    -0.09
    mony
    -0.09
    åĬłå¿«å»ºè®¾
    -0.09
    åĴĢ
    -0.09
    åĨħéĻĨ
    -0.08
    夤
    -0.08
     notebooks
    -0.08
    gent
    -0.08
     flashes
    -0.08
    emics
    -0.08
    POSITIVE LOGITS
    缤
    0.10
    çĿ¹
    0.10
    çĽĺ
    0.10
    éĶ¦ç»£
    0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.09
    ersions
    0.08
    äºĨåĩºæĿ¥
    0.08
    åģļæĪIJ
    0.08
    asper
    0.08
    arte
    0.08
    Activations Density 0.101%

    No Known Activations