© 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. 26519
    Prev
    Next
    INDEX
    Explanations

    greetings with there, all, everyone

    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
    çĽ¸å¯¹æĿ¥è¯´
    -0.09
     bÅĤ
    -0.08
    squ
    -0.08
    çĿĢå®ŀ
    -0.08
    èĤ¡æĿĥ
    -0.08
    æĪijçĪ¸
    -0.08
    奶油
    -0.08
    æĺ¯æ¯Ķè¾ĥ
    -0.08
    .rl
    -0.08
     Canterbury
    -0.08
    POSITIVE LOGITS
    ÑĥлÑĮ
    0.09
    æī¬
    0.09
    ampo
    0.09
    ÑĢаг
    0.08
    ares
    0.08
    å¡ŀ
    0.08
    èģĶç½ij
    0.08
     sos
    0.08
     Kul
    0.08
    åĴ«
    0.08
    Activations Density 0.014%

    No Known Activations