© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55692
    Prev
    Next
    INDEX
    Explanations

    holidays and traditions

    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
    .instant
    -0.09
    磫
    -0.09
    éĴ§
    -0.09
    伤å¿ĥ
    -0.09
    çħĮ
    -0.09
    æıIJåįĩäºĨ
    -0.09
    æĤ²
    -0.08
    çĶµç£ģ
    -0.08
    ç»Ŀ大å¤ļæķ°
    -0.08
    èĢģ大
    -0.08
    POSITIVE LOGITS
    åĩĨå¤ĩ好
    0.09
    æĭľ
    0.09
    éĥ¨åĪĨåľ°åĮº
    0.09
    佩æĪ´
    0.09
    è¿Ļåĩłå¤©
    0.08
    pars
    0.08
    bris
    0.08
    çģ¯çģ«
    0.08
    _locale
    0.08
    è¿Ļä¸Ģ天
    0.08
    Activations Density 0.069%

    No Known Activations