© 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. 52050
    Prev
    Next
    INDEX
    Explanations

    telecom and communications industry

    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
    磶
    -0.10
    ми
    -0.09
    leen
    -0.09
    æľĪ亮
    -0.09
    éħ±
    -0.09
    à¸Ĺรà¸ĩ
    -0.09
     forts
    -0.08
    yyy
    -0.08
    æīĵéĢļ
    -0.08
    iste
    -0.08
    POSITIVE LOGITS
    rary
    0.10
    åµ´
    0.10
    è¡Įä¸ļçļĦ
    0.10
    pra
    0.09
    å·¥ä½ľèĢħ
    0.09
    ÙĬÙĪÙĨ
    0.09
    巨头
    0.09
    å·¥ä½ľä»»åĬ¡
    0.08
    åıijè¾¾åĽ½å®¶
    0.08
    åįµ
    0.08
    Activations Density 0.022%

    No Known Activations