© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    Millennium Development Goals

    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
    寮
    -0.10
    orial
    -0.10
    ðŁı»
    -0.09
    TimeInterval
    -0.09
    warts
    -0.09
    oley
    -0.09
    æŀģ大
    -0.09
    èĤª
    -0.08
    furt
    -0.08
    çıŃåŃIJ
    -0.08
    POSITIVE LOGITS
    çĽ¸ä¼ł
    0.10
    èĪ¬
    0.09
    odzi
    0.09
    xsd
    0.09
    raph
    0.09
    è¹²
    0.09
    iswa
    0.09
    è¦ģ说
    0.08
    æıIJéĢŁ
    0.08
    ium
    0.08
    Activations Density 0.007%

    No Known Activations