© 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. 63385
    Prev
    Next
    INDEX
    Explanations

    smoke alarm

    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
    个å¤ļ
    -0.11
     микÑĢо
    -0.10
    ç¡Į
    -0.10
    urst
    -0.10
    æŀ¶åŃIJ
    -0.10
    åĩıåĢ¼
    -0.10
    å®ķ
    -0.09
    ä¾ĽéĶĢ
    -0.09
    å¤ļä½ĻçļĦ
    -0.09
    _ENT
    -0.09
    POSITIVE LOGITS
    åIJ¸çĥŁ
    0.10
    åľ¨åºĬä¸Ĭ
    0.09
    æ¶Īéĺ²å®īåħ¨
    0.09
    èººåľ¨åºĬä¸Ĭ
    0.09
    èѦ
    0.09
    å®Ī
    0.08
    åݨæĪ¿
    0.08
    woke
    0.08
     fireplace
    0.08
    åīĸæŀIJ
    0.08
    Activations Density 0.057%

    No Known Activations