© 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. 19447
    Prev
    Next
    INDEX
    Explanations

    randomized double-blind clinical trials

    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
    ummer
    -0.08
    åĩºèī²
    -0.08
    kin
    -0.08
    AME
    -0.08
    ãĤ·ãĥ³
    -0.08
    æ¶ĪåĮĸ
    -0.08
    aya
    -0.08
    Intro
    -0.08
    ite
    -0.08
    HING
    -0.08
    POSITIVE LOGITS
    eree
    0.10
    èįª
    0.10
    éĻįä½İæĪIJæľ¬
    0.09
    åŁ¹è®ŃæľºæŀĦ
    0.09
    è´«åĽ°åľ°åĮº
    0.09
    è¯ķéªĮ
    0.09
    误ä¼ļ
    0.09
    ìĸ¼
    0.09
    çĸĹæķĪ
    0.09
    glas
    0.09
    Activations Density 0.297%

    No Known Activations