© 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. 4466
    Prev
    Next
    INDEX
    Explanations

    room temperature conditions

    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
    深深
    -0.08
    licative
    -0.08
    æīİæł¹
    -0.08
    大声
    -0.08
    anio
    -0.08
     erle
    -0.08
    åĮĹ京æŶéĹ´
    -0.08
    é¢ī
    -0.08
    è¢«åĽ°
    -0.08
    çĬĩ
    -0.07
    POSITIVE LOGITS
    æĿ¡ä»¶ä¸ĭ
    0.15
     Conditions
    0.13
     temperatures
    0.13
    温度
    0.12
     conditions
    0.12
    æĿ¡ä»¶
    0.12
    çݯå¢ĥä¸ĭ
    0.12
    æ°Ķ温
    0.12
    conditions
    0.11
    Conditions
    0.11
    Activations Density 0.298%

    No Known Activations