© 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. 52869
    Prev
    Next
    INDEX
    Explanations

    lived in a place

    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
    /component
    -0.09
    .getParam
    -0.09
    CharacterSet
    -0.09
    æļ®
    -0.09
    æĬĬèĩªå·±
    -0.09
    .opend
    -0.09
    ä¸į对
    -0.09
    æģ¨
    -0.09
    jsc
    -0.09
    ISA
    -0.09
    POSITIVE LOGITS
    åľ¨è¿ĩåİ»
    0.09
    åīįåĩłå¹´
    0.09
    æ²¹èħ»
    0.09
    大åĬĽæİ¨è¿Ľ
    0.09
    æĮ¤
    0.08
    æĵł
    0.08
    åľ¨åĽ½å¤ĸ
    0.08
    åĢŃ
    0.08
    è¹²
    0.08
    åı°éĺ¶
    0.08
    Activations Density 0.038%

    No Known Activations