© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49141
    Prev
    Next
    INDEX
    Explanations

    SQL server programming and languages

    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
    æŁ¥éªĮ
    -0.11
    æł¸åĩĨ
    -0.10
    éĴī
    -0.10
    çĹ£
    -0.10
    磻
    -0.10
    åľ¨å®¶
    -0.09
    æ±ĩèģļ
    -0.09
    å¯Łçľĭ
    -0.09
    å¿ĥçIJĨåģ¥åº·
    -0.09
    æ¯ĭ
    -0.09
    POSITIVE LOGITS
    SQL
    0.10
    .Sql
    0.10
     SQL
    0.10
    èĩĨ
    0.09
    .SQL
    0.08
     sql
    0.08
     dare
    0.08
    boro
    0.08
    (sql
    0.08
    åĪĨ红
    0.08
    Activations Density 1.125%

    No Known Activations