© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7933
    Prev
    Next
    INDEX
    Explanations

    Dickens, Karamazov, Hogarth, homocysteinemia

    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
    è¯Ĺè¯į
    -0.08
    éĴİ
    -0.08
    icode
    -0.08
     visual
    -0.07
    è¯ķæİ¢
    -0.07
    åį±éĻ©
    -0.07
    以éĺ²
    -0.07
    orz
    -0.07
    æŀĩ
    -0.07
    oday
    -0.07
    POSITIVE LOGITS
    ç»Ń
    0.11
    storybook
    0.11
    è¿ŀè½½
    0.11
    åģ»
    0.10
    çļĦ人çī©
    0.10
    ä¸Ģæīĭ
    0.10
    渥
    0.10
    ENE
    0.09
    æŃĻ
    0.09
    iola
    0.09
    Activations Density 0.044%

    No Known Activations