© 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. 51347
    Prev
    Next
    INDEX
    Explanations

    cell transplantation or carcinoma

    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
    èĢħçļĦ
    -0.10
    sic
    -0.10
    æľŁåĨħ
    -0.09
    heet
    -0.08
    ä¸įå¿į
    -0.08
    tk
    -0.08
    ç»ıæµİä½ĵ
    -0.08
    ç«¿
    -0.08
    éŀŃ
    -0.08
    è¿Ľé©»
    -0.08
    POSITIVE LOGITS
    管çIJĨåĴĮ
    0.14
    çĸĹæ³ķ
    0.10
    æ´»åĬ¨ä¸Ń
    0.10
    _managed
    0.09
    swith
    0.09
    ÙĦÙĪÙĨ
    0.09
     therapy
    0.09
    ìĦŃ
    0.09
    èĢĢ
    0.09
    thood
    0.09
    Activations Density 0.593%

    No Known Activations