© 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. 11510
    Prev
    Next
    INDEX
    Explanations

    early life stages

    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
    ä¸ŃéĢĶ
    -0.09
    åħ¨ç¨ĭ
    -0.09
    æĪĪ
    -0.09
    lá
    -0.08
     juni
    -0.08
    çģŃ
    -0.08
    éĺ¶
    -0.08
     reck
    -0.08
    路线
    -0.08
    åĩ»
    -0.08
    POSITIVE LOGITS
    ä½ĵä¼ļåĪ°
    0.11
    å°±çŁ¥éģĵ
    0.11
    ä¸İæŶ
    0.10
    æĦıè¯ĨåĪ°
    0.10
    å°±è¦ģ
    0.09
    è¡·
    0.09
    认è¯ĨåĪ°
    0.09
    æ·±çŁ¥
    0.09
    éĩįå·¥
    0.09
    就被
    0.09
    Activations Density 0.026%

    No Known Activations