© 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. 37733
    Prev
    Next
    INDEX
    Explanations

    website navigation elements

    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
    俯
    -0.09
    itch
    -0.09
     EOF
    -0.08
    æĭĶ
    -0.08
    EOF
    -0.08
    æŁ¥çľĭåħ¨æĸĩ
    -0.08
    aris
    -0.08
    è¾į
    -0.08
    ç§ģèIJ¥
    -0.08
    家åĸ»æĪ·æĻĵ
    -0.08
    POSITIVE LOGITS
    lok
    0.09
    krit
    0.09
    adio
    0.08
    _procs
    0.08
    Eta
    0.08
    \xf
    0.08
    嵩
    0.08
    ãģĤãģ®
    0.08
    Pri
    0.08
     twó
    0.08
    Activations Density 3.792%

    No Known Activations