© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50806
    Prev
    Next
    INDEX
    Explanations

    military / combat / operations / advice

    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
    ief
    -0.10
    ç¼Ń
    -0.09
    UILTIN
    -0.08
     Templ
    -0.08
     Hass
    -0.08
    èĩªæĿĢ
    -0.08
     enrichment
    -0.08
    论
    -0.07
    Checksum
    -0.07
     Ryan
    -0.07
    POSITIVE LOGITS
    èĵģ
    0.10
    çļĭ
    0.10
    æĹı
    0.10
    å°Ĩèĩªå·±çļĦ
    0.10
    æ´²
    0.10
    åľ¨åĽ½å¤ĸ
    0.10
    åĮ»èį¯
    0.09
     Furniture
    0.09
    éĩįä»»
    0.09
    oure
    0.09
    Activations Density 0.087%

    No Known Activations