© 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. 37124
    Prev
    Next
    INDEX
    Explanations

    weather and temperature descriptions

    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
    åĪ»
    -0.10
    ä¸ĢåĪ»
    -0.10
     нап
    -0.10
    _lineno
    -0.09
    åħ¨åľº
    -0.09
    çĶ¸
    -0.09
    æĺ§
    -0.09
    åħ¨åŁŁ
    -0.09
    人æ°Ķ
    -0.09
    é¾Ľ
    -0.09
    POSITIVE LOGITS
     ÐľÐ¾Ñģкве
    0.09
    ãģĹãģ
    0.08
     I
    0.08
    å¤ĸéĿ¢
    0.08
    æĪijè¿ĺæĺ¯
    0.08
    mps
    0.08
    å¥Ī
    0.08
    BEL
    0.08
    åľ¨åĮĹ京
    0.08
    BOUND
    0.08
    Activations Density 0.041%

    No Known Activations